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

    Neuronpedia

    INDEX
    Explanations

    s

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    uggest
    -0.11
    начала
    -0.09
    chool
    -0.09
    CHOOL
    -0.09
    lightly
    -0.09
    creen
    -0.09
    amples
    -0.09
    omething
    -0.09
    pecial
    -0.09
    pecific
    -0.09
    POSITIVE LOGITS
    Sab
    0.08
    .Seek
    0.08
     Sor
    0.08
     sire
    0.08
     Sight
    0.08
     Sab
    0.08
     SCT
    0.08
     sop
    0.08
     sul
    0.08
     SD
    0.08
    Act Density 3.834%

    No Known Activations