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

    Neuronpedia

    INDEX
    Explanations

    numbers and their combinations

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

    numbers and units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ,
    -0.53
     in
    -0.45
     “
    -0.45
    ↵↵
    -0.44
    ↵
    -0.43
     "
    -0.42
     with
    -0.42
     (
    -0.41
    ’
    -0.40
     at
    -0.40
    POSITIVE LOGITS
     EconPapers
    0.98
     ब्रेकडाउन
    0.89
    AddTagHelper
    0.84
    iſten
    0.81
     utafitiHapana
    0.81
    iſen
    0.80
    tonsoft
    0.80
    WriteTagHelper
    0.78
    ſchaft
    0.77
     kaarangay
    0.77
    Act Density 0.082%

    No Known Activations