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

    Neuronpedia

    INDEX
    Explanations

    específ

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    东省
    -0.07
     �
    -0.07
     دف
    -0.06
     vl
    -0.06
    ζε
    -0.06
     منت
    -0.06
    _Pods
    -0.06
    $values
    -0.06
     olumlu
    -0.06
     modest
    -0.06
    POSITIVE LOGITS
     amplified
    0.07
     Byrne
    0.07
    olls
    0.07
    assed
    0.06
     truly
    0.06
     details
    0.06
    apellido
    0.06
     GT
    0.06
    ,V
    0.06
     Rein
    0.06
    Act Density 0.014%

    No Known Activations