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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and expressions

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

    conditions or variables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Differenz
    -0.42
     judiciaire
    -0.41
    differ
    -0.40
     deviate
    -0.38
     mundos
    -0.38
    tituzione
    -0.38
    führt
    -0.37
     différent
    -0.37
     ruidos
    -0.37
     gömlek
    -0.36
    POSITIVE LOGITS
    protoimpl
    0.63
     Савезне
    0.53
    AddTagHelper
    0.51
    elemField
    0.51
    rrggbb
    0.49
    IntoConstraints
    0.49
    UnusedPrivate
    0.49
     noDo
    0.49
     kaarangay
    0.48
    ⎨
    0.48
    Act Density 0.115%

    No Known Activations