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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     elemento
    -0.07
     admitting
    -0.07
    、この
    -0.07
     Standards
    -0.07
     dispersed
    -0.07
     offended
    -0.07
     Historic
    -0.07
     dispozici
    -0.07
     sponsors
    -0.06
     listeners
    -0.06
    POSITIVE LOGITS
    InternalEnumerator
    0.06
    tolua
    0.06
     saat
    0.06
     joy
    0.06
     motor
    0.06
    Unlike
    0.06
     jika
    0.06
     конт
    0.06
    /#{
    0.06
    _xor
    0.06
    Act Density 0.000%

    No Known Activations