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

    Neuronpedia

    INDEX
    Explanations

    Code and licenses

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    成立
    -0.07
    _extended
    -0.06
     exemptions
    -0.06
    ιθ
    -0.06
     surrounds
    -0.06
    |\
    -0.06
    友
    -0.06
     thresh
    -0.06
    chyb
    -0.06
    광고
    -0.06
    POSITIVE LOGITS
    бора
    0.06
    jte
    0.06
     plagiar
    0.06
     enamel
    0.06
    こと
    0.06
     toler
    0.06
    rasing
    0.06
    بن
    0.06
     zoning
    0.06
    /tr
    0.06
    Act Density 0.004%

    No Known Activations