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

    Neuronpedia

    INDEX
    Explanations

    question

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     skinny
    -0.07
     cars
    -0.07
    pheres
    -0.07
    ROID
    -0.07
     chicago
    -0.07
     удов
    -0.07
     portraying
    -0.06
     지정
    -0.06
     Discord
    -0.06
    GRAPH
    -0.06
    POSITIVE LOGITS
    ��
    0.07
     HI
    0.06
    .tem
    0.06
     Pam
    0.06
     hoe
    0.06
     qx
    0.06
    /*/
    0.06
     시
    0.06
    ~":"
    0.06
    LatLng
    0.06
    Act Density 0.000%

    No Known Activations