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

    Neuronpedia

    INDEX
    Explanations

    references to labels in various contexts

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

    label and labels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Christi
    -0.52
    atmosphère
    -0.49
    AppMethodBeat
    -0.48
    extrême
    -0.48
     McKinney
    -0.48
    Five
    -0.47
    windowFixed
    -0.47
     Goodrich
    -0.46
     Gon
    -0.45
    five
    -0.45
    POSITIVE LOGITS
     label
    2.08
     Label
    1.86
     LABEL
    1.76
    label
    1.70
     labels
    1.61
     Labels
    1.59
    Label
    1.58
    LABEL
    1.48
    getLabel
    1.38
    Labels
    1.31
    Act Density 0.024%

    No Known Activations