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

    Neuronpedia

    INDEX
    Explanations

    )

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .getenv
    -0.08
    痘
    -0.07
     Vern
    -0.07
     Responsible
    -0.07
     Cannabis
    -0.07
    兕
    -0.07
     Krishna
    -0.07
    正好
    -0.07
    orghini
    -0.07
    vas
    -0.07
    POSITIVE LOGITS
    记
    0.07
     Codec
    0.07
    });
↵
↵
    0.07
     static
    0.06
    umption
    0.06
    UTH
    0.06
    心得体会
    0.06
    קדש
    0.06
     yavaş
    0.06
    绎
    0.06
    Act Density 0.001%

    No Known Activations