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

    Neuronpedia

    INDEX
    Explanations

    programming code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rõ
    -0.08
    1
    -0.08
    Key
    -0.08
     Holy
    -0.07
     key
    -0.07
    KEY
    -0.06
    .pipe
    -0.06
     See
    -0.06
    wire
    -0.06
     babe
    -0.06
    POSITIVE LOGITS
    ation
    0.14
    ations
    0.12
    ATION
    0.11
    gradation
    0.10
     Reduction
    0.10
     reduction
    0.09
    TION
    0.09
    vation
    0.09
    ACEMENT
    0.08
    ATIONS
    0.08
    Act Density 1.708%

    No Known Activations