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

    Neuronpedia

    INDEX
    Explanations

    mathematical terms and operations in equations and expressions

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

    math and numerical calculations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     barbati
    -0.41
     butterknife
    -0.35
    ウンジ
    -0.33
     storici
    -0.33
     écrivain
    -0.33
     TextAppearance
    -0.32
    Gr
    -0.32
    ปล
    -0.32
     tulee
    -0.31
     DC
    -0.31
    POSITIVE LOGITS
     мәкал
    0.68
     للاسماء
    0.64
     '\\;'
    0.59
    adaptiveStyles
    0.55
    Autoritní
    0.52
    Rüyada
    0.49
    complexType
    0.48
    xnn
    0.47
    rungsseite
    0.47
    ProgressHUD
    0.47
    Act Density 0.000%

    No Known Activations