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

    Neuronpedia

    INDEX
    Explanations

    instances of hope and ambition

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

    Follows forms of "be" ("is", "was", "been")

    np_acts-logits-general · gemini-2.0-flash

    honour and positive affirmation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GraphicsUnit
    -0.68
     تضيفلها
    -0.66
    OGND
    -0.65
    rungsseite
    -0.65
    CppCodeGen
    -0.64
     otomatig
    -0.63
     autorytatywna
    -0.62
     informée
    -0.62
    Архівовано
    -0.59
     '\\;'
    -0.57
    POSITIVE LOGITS
     fø
    0.32
     my
    0.31
     perasaan
    0.30
    AlterField
    0.30
    对我
    0.29
    Precautionary
    0.29
     MonoBehaviour
    0.28
     Feeling
    0.28
     feeling
    0.28
    UnknownFieldSet
    0.27
    Act Density 0.134%

    No Known Activations