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

    Neuronpedia

    INDEX
    Explanations

    references to components or parts of a mechanical or technical system

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

    part components

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Hochspringen
    -0.50
    queryInterface
    -0.45
     eşofman
    -0.44
     toalha
    -0.44
    enyum
    -0.43
    Jereo
    -0.42
     Geneva
    -0.41
    nexpected
    -0.41
    NESDAY
    -0.41
     poisons
    -0.41
    POSITIVE LOGITS
     part
    1.35
    part
    1.34
    Part
    1.27
     parts
    1.20
     Part
    1.16
    parts
    1.05
    Parts
    1.05
     Parts
    1.02
     PART
    1.02
     PARTS
    0.96
    Act Density 0.036%

    No Known Activations