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

    Neuronpedia

    INDEX
    Explanations

    variables

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    —to
    -0.07
    .BorderFactory
    -0.07
    .sess
    -0.07
     от
    -0.07
    —for
    -0.07
     апр
    -0.07
    —at
    -0.06
     off
    -0.06
     Hoffman
    -0.06
    =http
    -0.06
    POSITIVE LOGITS
     variable
    0.15
     variables
    0.15
     Variable
    0.12
    Variable
    0.12
     Variables
    0.11
    variable
    0.10
     VARIABLE
    0.10
    variables
    0.10
    _variable
    0.09
    -variable
    0.09
    Act Density 0.023%

    No Known Activations