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

    Neuronpedia

    INDEX
    Explanations

    public

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Rein
    -0.06
    Speech
    -0.06
    pill
    -0.06
     rack
    -0.06
     dismal
    -0.06
     관한
    -0.06
     служ
    -0.06
     코드
    -0.06
     membuat
    -0.06
    Tech
    -0.06
    POSITIVE LOGITS
    .visualization
    0.07
    ๑
    0.06
     Chief
    0.06
     TOOL
    0.06
    NC
    0.06
    <class
    0.06
     slapped
    0.06
    _PED
    0.06
    uded
    0.06
    ে
    0.06
    Act Density 0.006%

    No Known Activations