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

    Neuronpedia

    INDEX
    Explanations

    Dialogue

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     บาง
    -0.07
    すぐ
    -0.07
    [code
    -0.07
    _house
    -0.07
     单
    -0.07
    _THREAD
    -0.07
    atif
    -0.06
     doivent
    -0.06
     Georgian
    -0.06
    .EMPTY
    -0.06
    POSITIVE LOGITS
     هج
    0.07
    happy
    0.07
    Lou
    0.06
    Bill
    0.06
    amics
    0.06
     thrilled
    0.06
    况
    0.06
     tuy
    0.06
     Municip
    0.06
     takson
    0.06
    Act Density 0.073%

    No Known Activations