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

    Neuronpedia

    INDEX
    Explanations

    titles or named entities within a specific context, particularly related to categories or classifications

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

    HTML or LaTeX formatting

    np_acts-logits-general · gemini-2.0-flash

    markup or code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     
    -0.77
     fl
    -0.64
    fl
    -0.62
    viewWillAppear
    -0.61
     }}$}
    -0.60
     fi
    -0.57
     fupp
    -0.57
    ientôt
    -0.56
    #%%
    -0.56
     Jefus
    -0.55
    POSITIVE LOGITS
    <b>
    1.66
    </b>
    0.99
    <i>
    0.96
    </i>
    0.95
    /*
    0.91
     /*
    0.86
    dfrac
    0.82
     ${\
    0.74
     {@
    0.66
    <sup>
    0.61
    Act Density 0.435%

    No Known Activations