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

    Neuronpedia

    INDEX
    Explanations

    Foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cst
    -0.07
    CHIP
    -0.07
     framework
    -0.07
    _button
    -0.07
    _dst
    -0.07
    psych
    -0.07
    .bt
    -0.07
    yps
    -0.06
    羹
    -0.06
    proxy
    -0.06
    POSITIVE LOGITS
     здоров
    0.08
    anagan
    0.08
     colleagues
    0.07
    ลาน
    0.06
    停车场
    0.06
    ゾ
    0.06
    协同发展
    0.06
     Gary
    0.06
    Salary
    0.06
     Campos
    0.06
    Act Density 0.010%

    No Known Activations