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

    Neuronpedia

    INDEX
    Explanations

    code tags and identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Guten
    -0.85
    Transcripción
    -0.79
    ='\
    -0.78
    ={};
    -0.78
    Audiobook
    -0.77
    УДК
    -0.77
     vom
    -0.75
    Abra
    -0.75
     konkrete
    -0.74
    Frans
    -0.73
    POSITIVE LOGITS
    Lay
    1.01
    LAY
    0.88
     Lay
    0.88
    osť
    0.81
    hrter
    0.80
    Cube
    0.78
    EDITOR
    0.78
    EAC
    0.77
    ARMA
    0.77
    URL
    0.77
    Act Density 0.002%

    No Known Activations