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

    Neuronpedia

    INDEX
    Explanations

    terms related to revelation or exposure of truth and identities

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

    revealing or exposing secrets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Ink
    -0.34
     تقد
    -0.33
    scroller
    -0.31
     pilo
    -0.30
    epres
    -0.30
     rhestr
    -0.30
     mutu
    -0.30
    happ
    -0.30
     GC
    -0.30
     vag
    -0.29
    POSITIVE LOGITS
     Exposed
    0.87
     exposed
    0.83
    Exposed
    0.77
    exposed
    0.74
     avsl
    0.74
     exposes
    0.72
    暴露
    0.69
     exposing
    0.69
     descubierto
    0.66
     expose
    0.63
    Act Density 0.085%

    No Known Activations