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

    Neuronpedia

    INDEX
    Explanations

    Code documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Confederate
    -0.07
    UGE
    -0.07
    -fe
    -0.07
     alters
    -0.07
    xBE
    -0.06
     Cups
    -0.06
    убли
    -0.06
     طريق
    -0.06
     TERMIN
    -0.06
     mars
    -0.06
    POSITIVE LOGITS
    pch
    0.07
     hvor
    0.06
    rak
    0.06
     blossom
    0.06
     ◎
    0.06
    roducing
    0.06
    luž
    0.06
    sian
    0.06
     conosc
    0.06
    要
    0.06
    Act Density 0.010%

    No Known Activations