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

    Neuronpedia

    INDEX
    Explanations

    parameter

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ж
    -0.07
     Duck
    -0.07
     Ecc
    -0.07
     Dix
    -0.06
     courtesy
    -0.06
    readOnly
    -0.06
     OLD
    -0.06
    ickle
    -0.06
     ly
    -0.06
     Lust
    -0.06
    POSITIVE LOGITS
     parameters
    0.12
    Params
    0.11
     parameter
    0.11
    parameters
    0.11
     Param
    0.10
    prm
    0.10
    _params
    0.10
     param
    0.10
    params
    0.10
    parameter
    0.09
    Act Density 0.029%

    No Known Activations