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

    Neuronpedia

    INDEX
    Explanations

    host

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sigma
    -0.07
    -written
    -0.06
     편
    -0.06
    /math
    -0.06
    acking
    -0.06
    .RowCount
    -0.06
     "\\"
    -0.06
    .Exp
    -0.06
     newline
    -0.06
    〜
    -0.06
    POSITIVE LOGITS
    ghost
    0.07
    وان
    0.07
    Gay
    0.06
    stří
    0.06
     klar
    0.06
    �
    0.06
    вою
    0.06
    �
    0.06
     Photo
    0.06
    astro
    0.06
    Act Density 0.005%

    No Known Activations