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

    Neuronpedia

    INDEX
    Explanations

    computer code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     olay
    -0.07
     tầng
    -0.06
    耶
    -0.06
    十三
    -0.06
     resh
    -0.06
     澳
    -0.06
    _OT
    -0.06
    _REPO
    -0.06
     aun
    -0.05
    ---
    -0.05
    POSITIVE LOGITS
     getFile
    0.08
     dictionaryWith
    0.07
    Ohio
    0.07
    DatePicker
    0.07
     Anthrop
    0.06
     cultivate
    0.06
     debian
    0.06
    Challenge
    0.06
    っぱい
    0.06
    ancia
    0.06
    Act Density 0.000%

    No Known Activations