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

    Neuronpedia

    INDEX
    Explanations

    sentences that include punctuation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    dot file extensions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    enumi
    -0.50
     myſelf
    -0.48
     becauſe
    -0.48
     alarme
    -0.48
     Anspruch
    -0.48
     Anexo
    -0.47
    StackNavigator
    -0.47
     desmotivaciones
    -0.46
    來說
    -0.46
    ：
    -0.46
    POSITIVE LOGITS
     .
    0.91
     (_.
    0.83
     /\.
    0.82
     (.
    0.80
     $.
    0.79
     [.
    0.79
     <.
    0.78
    (.
    0.77
     ($.
    0.75
     ~/.
    0.73
    Act Density 0.068%

    No Known Activations