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

    Neuronpedia

    INDEX
    Explanations

    new experiences/feelings

    np_max-act · gemini-2.0-flash

    The neuron is effectively dead—it never activates (all its activation values are zero).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    urança
    -0.06
    .Small
    -0.06
     Crest
    -0.06
     تجربه
    -0.06
    (gen
    -0.06
     vyž
    -0.06
    GING
    -0.06
    чний
    -0.06
    _corpus
    -0.06
    슨
    -0.06
    POSITIVE LOGITS
    (QtGui
    0.07
     dah
    0.07
     sce
    0.07
     �
    0.07
     hiring
    0.07
     answer
    0.06
    =<
    0.06
     Range
    0.06
    ト
    0.06
    bang
    0.06
    Act Density 0.016%

    No Known Activations