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

    Neuronpedia

    INDEX
    Explanations

    mentions of ignorance and turning away from injustice

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    iastes
    -0.75
    anair
    -0.75
    ContentAsync
    -0.74
    LEncoder
    -0.74
    bootstrapcdn
    -0.72
     мәкалә
    -0.71
    Tikang
    -0.70
     autorytatywna
    -0.69
    BarStyle
    -0.69
    LElement
    -0.68
    POSITIVE LOGITS
     ignore
    0.52
    zub
    0.52
     deaf
    0.48
     pretend
    0.45
     ignores
    0.45
     past
    0.44
     ignored
    0.44
     recep
    0.42
    敏
    0.42
     ignoring
    0.42
    Act Density 0.113%

    No Known Activations