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

    Neuronpedia

    INDEX
    Explanations

    mathematical texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     adolescence
    -0.07
    Android
    -0.06
     purity
    -0.06
    ﺘ
    -0.06
    ornecedor
    -0.06
     Songs
    -0.06
     ці
    -0.06
     إلى
    -0.06
    مش
    -0.06
    iд
    -0.05
    POSITIVE LOGITS
    deliver
    0.07
    _fill
    0.07
     torino
    0.06
     slopes
    0.06
    cantidad
    0.06
    /base
    0.06
    Unable
    0.06
    گونه
    0.06
    odable
    0.06
    >↵↵↵↵
    0.06
    Act Density 0.029%

    No Known Activations