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

    Neuronpedia

    INDEX
    Explanations

    legal denials

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     javascript
    -0.08
    (Table
    -0.07
     eldest
    -0.07
     published
    -0.07
     Node
    -0.07
     bond
    -0.07
    大學
    -0.06
    (ERROR
    -0.06
     Video
    -0.06
     محدود
    -0.06
    POSITIVE LOGITS
    anel
    0.06
    -enabled
    0.06
    ."\
    0.06
    긴
    0.06
    dük
    0.06
    .sign
    0.06
     Söz
    0.06
    _ord
    0.06
    -off
    0.06
    δος
    0.06
    Act Density 0.018%

    No Known Activations