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

    Neuronpedia

    INDEX
    Explanations

    fit

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Wick
    -0.07
    /icon
    -0.06
     además
    -0.06
     비밀
    -0.06
    ुज
    -0.06
     Quint
    -0.06
     rept
    -0.06
     spanning
    -0.06
     TG
    -0.06
     |=
    -0.06
    POSITIVE LOGITS
     soften
    0.07
     χρό
    0.07
    átor
    0.06
    depending
    0.06
     Ea
    0.06
    GRP
    0.06
     découvrir
    0.06
     exig
    0.06
    AndView
    0.06
    Muon
    0.06
    Act Density 0.012%

    No Known Activations