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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Основ
    -0.07
    뗍
    -0.07
     BMI
    -0.07
    츤
    -0.06
    .Timer
    -0.06
    CppObject
    -0.06
    ’aut
    -0.06
    볜
    -0.06
    utom
    -0.06
    奥地
    -0.06
    POSITIVE LOGITS
    _codes
    0.07
     revel
    0.07
    们的
    0.07
    敢于
    0.07
    机
    0.07
    _ds
    0.07
     INSTALL
    0.06
    シュ
    0.06
    -sample
    0.06
     sourced
    0.06
    Act Density 0.000%

    No Known Activations