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

    Neuronpedia

    INDEX
    Explanations

    code structures or functions related to testing in programming

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

    specific tokens followed by other tokens

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RenderAtEndOf
    -0.67
    RegressionTest
    -0.64
     Italijanski
    -0.58
    Autoritní
    -0.58
     يتيمه
    -0.56
    хьтан
    -0.56
     الرياضيه
    -0.52
    IsContent
    -0.51
     оригіналу
    -0.49
    berdayakan
    -0.49
    POSITIVE LOGITS
    gonic
    0.72
    gorm
    0.47
     DataTypes
    0.40
    ManyToMany
    0.39
     Position
    0.35
    iastes
    0.35
    VolleyError
    0.32
    tionalität
    0.32
     indisponible
    0.31
    SuccessListener
    0.31
    Act Density 0.001%

    No Known Activations