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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Fecha
    -0.07
     tame
    -0.07
     tid
    -0.07
     Encrypt
    -0.07
    taş
    -0.06
     Rum
    -0.06
    Hibernate
    -0.06
     Funeral
    -0.06
     UserId
    -0.06
    _trace
    -0.06
    POSITIVE LOGITS
    aic
    0.07
     alespoň
    0.06
    orio
    0.06
     alex
    0.06
     य
    0.06
     count
    0.06
     �
    0.06
    �
    0.06
    ateful
    0.06
     아래
    0.06
    Act Density 0.119%

    No Known Activations