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

    Neuronpedia

    INDEX
    Explanations

    internet

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Doug
    -0.07
    /change
    -0.07
    .Al
    -0.06
    uplic
    -0.06
    Axis
    -0.06
     Elvis
    -0.06
     apenas
    -0.06
    ison
    -0.06
     경우
    -0.06
    _SW
    -0.06
    POSITIVE LOGITS
    amız
    0.07
     imprisonment
    0.06
     مس
    0.06
     manufacture
    0.06
     recruits
    0.06
    출장
    0.06
     création
    0.06
    生物
    0.06
     performs
    0.06
    .pageSize
    0.06
    Act Density 0.002%

    No Known Activations