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

    Neuronpedia

    INDEX
    Explanations

    Code and special characters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     designated
    -0.08
     passes
    -0.08
    Bindings
    -0.08
     receives
    -0.08
    recv
    -0.07
     salarial
    -0.07
    Getter
    -0.07
     Lieb
    -0.07
    Geb
    -0.07
     brib
    -0.07
    POSITIVE LOGITS
     dog's
    0.08
    ="/"
    0.08
     thưởng
    0.08
     باہر
    0.08
     گئی
    0.08
     مسلمانوں
    0.08
    ği
    0.08
     gemeins
    0.08
     فرض
    0.08
     نیست
    0.07
    Act Density 0.001%

    No Known Activations