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

    Neuronpedia

    INDEX
    Explanations

    Non-English characters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (require
    -0.06
     DeepCopy
    -0.06
     ignorance
    -0.06
    WritableDatabase
    -0.06
    ricao
    -0.06
     scor
    -0.06
     )[
    -0.06
     усл
    -0.06
    /go
    -0.06
    (pre
    -0.06
    POSITIVE LOGITS
    خاص
    0.07
     nem
    0.07
     lambda
    0.06
    -loving
    0.06
    ologi
    0.06
    Grace
    0.06
    thank
    0.06
    ayım
    0.06
    -&
    0.06
     γλώ
    0.06
    Act Density 0.022%

    No Known Activations