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

    Neuronpedia

    INDEX
    Explanations

    elements related to deception and manipulation

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

    Two or three letter prefixes

    np_acts-logits-general · gemini-2.0-flash

    combining prefixes with suffixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .
    -0.71
    ,
    -0.65
    ⓘ
    -0.64
    ↵↵
    -0.62
    ↵
    -0.58
    ↵↵↵
    -0.57
    :
    -0.56
    以外
    -0.55
     juvenil
    -0.55
     (
    -0.53
    POSITIVE LOGITS
    éphane
    0.76
    ésult
    0.74
    ientras
    0.73
    ſem
    0.73
    arangay
    0.72
    ugeot
    0.72
    ſſer
    0.72
    ratulations
    0.71
    ulongan
    0.71
    IBLIO
    0.71
    Act Density 0.979%

    No Known Activations