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

    Neuronpedia

    INDEX
    Explanations

    terms related to ignoring or neglecting factors in data analysis

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

    "Ign", "ign", or "gn" prefixes

    np_acts-logits-general · gemini-2.0-flash

    ign and gn prefixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Marat
    -0.55
    AutoScaleMode
    -0.45
     PÉ
    -0.45
     endregion
    -0.45
     Kammer
    -0.43
     Sel
    -0.43
    kamer
    -0.41
    ;'>
    -0.41
     متحده
    -0.41
     Sy
    -0.41
    POSITIVE LOGITS
     Gn
    0.85
    Ign
    0.83
     gn
    0.81
    COGN
    0.77
     GN
    0.76
    agno
    0.76
     IGN
    0.73
     ligiloj
    0.72
     recogni
    0.72
     Ign
    0.71
    Act Density 0.186%

    No Known Activations