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

    Neuronpedia

    INDEX
    Explanations

    patterns related to negative values or separations in mathematical contexts

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

    sr-only

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ❋
    -0.65
    !*\
    -0.53
     importado
    -0.50
     avulla
    -0.48
     виправивши
    -0.45
    enderror
    -0.43
     EconPapers
    -0.39
     kautta
    -0.39
     asesinado
    -0.38
     importación
    -0.37
    POSITIVE LOGITS
     defaultstate
    0.60
    complexContent
    0.52
     gas
    0.51
    elemField
    0.50
    AxisAlignment
    0.50
     يتيمه
    0.47
    sizeCache
    0.46
     vertical
    0.46
     span
    0.45
     hiding
    0.45
    Act Density 0.000%

    No Known Activations