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

    Neuronpedia

    INDEX
    Explanations

    statements and themes related to denial and self-deception

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

    denial of reality

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    差点
    -0.39
     icônes
    -0.38
     jugado
    -0.37
     pictograms
    -0.36
     AttributeSet
    -0.35
    MigrationBuilder
    -0.35
    OCCURRED
    -0.35
    mimeType
    -0.34
    ynchronously
    -0.33
    ophytes
    -0.33
    POSITIVE LOGITS
     ignoring
    0.57
     denial
    0.56
    denial
    0.52
     utafitiHapana
    0.50
     ostrich
    0.49
     acknowledging
    0.49
     Denial
    0.49
     ignore
    0.48
     arşivlendi
    0.48
     acknowledgment
    0.48
    Act Density 0.163%

    No Known Activations