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

    Neuronpedia

    INDEX
    Explanations

    occurrences of labels and their associated values in a structured format

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

    "label" following specific words

    np_acts-logits-general · gemini-2.0-flash

    my label

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tow
    -0.52
     nî
    -0.49
     entsch
    -0.46
     متعلقه
    -0.46
    toe
    -0.46
    Portail
    -0.45
    course
    -0.45
    FormTagHelper
    -0.44
    river
    -0.44
    atars
    -0.44
    POSITIVE LOGITS
     label
    4.04
    label
    3.67
     Label
    3.51
    Label
    3.25
     labels
    3.18
     LABEL
    3.13
    LABEL
    2.90
     Labels
    2.87
     labeling
    2.84
     labelling
    2.64
    Act Density 0.126%

    No Known Activations