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

    Neuronpedia

    INDEX
    Explanations

    layers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Trevor
    -0.08
    річ
    -0.07
     policeman
    -0.07
     Sob
    -0.07
    searchModel
    -0.07
     Setup
    -0.07
    ["$
    -0.06
    -Up
    -0.06
    िद
    -0.06
    xlsx
    -0.06
    POSITIVE LOGITS
    _layers
    0.07
     shouldn
    0.06
    .Hash
    0.06
     değ
    0.06
    -import
    0.06
     crude
    0.06
    ollow
    0.06
    [:,
    0.06
     porn
    0.06
    _beh
    0.06
    Act Density 0.004%

    No Known Activations