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

    Neuronpedia

    INDEX
    Explanations

    references to individuals, particularly those associated with the name "Mal"

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

    Texts starting with "Mar" or "Mal"

    np_acts-logits-general · gemini-2.0-flash

    words starting with Mar or Mal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Theſe
    -1.73
     itſelf
    -1.72
     myſelf
    -1.64
     Anſ
    -1.58
     faſt
    -1.52
     pleaſure
    -1.51
     purpoſe
    -1.49
     ་་
    -1.46
    BibitemShut
    -1.45
     reaſon
    -1.44
    POSITIVE LOGITS
    S
    1.00
    G
    0.95
    P
    0.92
    R
    0.91
     Ar
    0.91
     Al
    0.91
    Al
    0.90
    O
    0.90
    B
    0.90
    Ar
    0.89
    Act Density 0.647%

    No Known Activations