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

    Neuronpedia

    INDEX
    Explanations

    references to personal experiences and self-identity

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

    you and your experiences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ValueStyle
    -0.58
     ब्रेकडाउन
    -0.46
     otomatig
    -0.43
    IsContent
    -0.42
    ConstraintMaker
    -0.41
    хема
    -0.40
    uttosto
    -0.40
    GraphicsUnit
    -0.37
    󠁢
    -0.37
     Normdatei
    -0.36
    POSITIVE LOGITS
    RTEX
    0.49
     aspirations
    0.48
     aspiration
    0.47
     Aspir
    0.46
     fores
    0.46
    يكب
    0.44
    …?
    0.43
    ngdoc
    0.43
    \{\\
    0.43
    前任
    0.41
    Act Density 0.007%

    No Known Activations