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

    Neuronpedia

    INDEX
    Explanations

    param

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     easily
    -0.07
     �
    -0.07
     Zahl
    -0.07
    ller
    -0.07
    enery
    -0.07
    есь
    -0.07
    乐
    -0.07
     Bey
    -0.06
     ож
    -0.06
    Er
    -0.06
    POSITIVE LOGITS
    Params
    0.12
     params
    0.11
    _params
    0.11
    params
    0.11
    Param
    0.10
    .params
    0.10
    .Param
    0.09
    	params
    0.09
    _param
    0.09
    routeParams
    0.09
    Act Density 0.008%

    No Known Activations