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

    Neuronpedia

    INDEX
    Explanations

    mentions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _subnet
    -0.07
    -read
    -0.07
    	conf
    -0.07
     Vision
    -0.06
    link
    -0.06
    ictures
    -0.06
    :
↵
    -0.06
    _cut
    -0.06
     Hunter
    -0.06
     nets
    -0.06
    POSITIVE LOGITS
    ////////////////////////////////////////////////////////////////////////////////////////////////
    0.07
     kaynağı
    0.07
    phalt
    0.07
     bás
    0.06
     rapide
    0.06
     süresi
    0.06
    qd
    0.06
     esa
    0.06
     ejec
    0.06
     استفاده
    0.06
    Act Density 0.070%

    No Known Activations