Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    occurrences of edits, updates, or changes in context within discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Text edits, often marked with "EDIT" or "UPDATE"

    np_acts-logits-general · gemini-2.0-flash

    corrections or updates after edits

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Tikang
    -0.44
    /***/
    -0.41
    wpi
    -0.39
     propOrder
    -0.37
    FlatAppearance
    -0.36
     neumáticos
    -0.36
    PendingIntent
    -0.36
     rosca
    -0.34
     inför
    -0.33
    stdc
    -0.32
    POSITIVE LOGITS
     createState
    0.51
     CreateTagHelper
    0.50
    WithFormat
    0.48
     للمعارف
    0.47
     يتيمه
    0.47
    今度は
    0.47
    oops
    0.46
     שוליים
    0.46
    Cyfarwyddwr
    0.44
    thâu
    0.44
    Act Density 0.237%

    No Known Activations