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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hepat
    -0.08
     bara
    -0.07
     convicted
    -0.07
    ﰞ
    -0.06
    ቴ
    -0.06
    .hostname
    -0.06
     leggings
    -0.06
     throm
    -0.06
     raping
    -0.06
     atrocities
    -0.06
    POSITIVE LOGITS
    的区别
    0.08
    Canceled
    0.07
     Length
    0.07
     superf
    0.07
    %
    0.07
    writers
    0.07
     wrinkles
    0.07
     wohl
    0.07
    _EQ
    0.07
    ------+------+
    0.07
    Act Density 0.021%

    No Known Activations