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

    Neuronpedia

    INDEX
    Explanations

    spelling variations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Wien
    -0.07
     Hubb
    -0.07
     اخ
    -0.06
     bleak
    -0.06
     Cs
    -0.06
    rhs
    -0.06
     člověk
    -0.06
    енням
    -0.06
    recv
    -0.06
    quiz
    -0.06
    POSITIVE LOGITS
    (cors
    0.07
    尘
    0.07
             
    0.07
    _VARIABLE
    0.06
    duration
    0.06
    Normalized
    0.06
    更加
    0.06
    soap
    0.06
    为空
    0.06
     thickness
    0.06
    Act Density 0.003%

    No Known Activations