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

    Neuronpedia

    INDEX
    Explanations

    porch

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     therap
    -0.07
    amide
    -0.07
     آ
    -0.07
    Gravity
    -0.07
     も
    -0.07
     Γεω
    -0.06
     numbers
    -0.06
     віль
    -0.06
     mel
    -0.06
    Filtered
    -0.06
    POSITIVE LOGITS
     porch
    0.15
     dive
    0.07
    !=(
    0.07
     Por
    0.07
     dönüş
    0.06
    entlich
    0.06
     CVS
    0.06
    constexpr
    0.06
    ewriter
    0.06
    .kind
    0.06
    Act Density 0.001%

    No Known Activations