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

    Neuronpedia

    INDEX
    Explanations

    hyperparameter

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     jack
    -0.06
    (src
    -0.06
     getService
    -0.06
    _values
    -0.06
    aviors
    -0.06
     porque
    -0.06
     entries
    -0.06
    >null
    -0.06
    AMPLE
    -0.06
     marketers
    -0.06
    POSITIVE LOGITS
    =head
    0.07
    _parameters
    0.06
     Happy
    0.06
     Troll
    0.06
    .Serializer
    0.06
     tern
    0.06
    ################################################################
    0.06
     Athletic
    0.06
    ================================================================
    0.06
     acab
    0.06
    Act Density 0.003%

    No Known Activations