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

    Neuronpedia

    INDEX
    Explanations

    terms related to hiding or concealment

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

    hiding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    EFIAPI
    -0.47
    󠁴
    -0.46
     للاسماء
    -0.46
    AndEndTag
    -0.44
     FetchType
    -0.44
    
    -0.43
     lamina
    -0.43
    AntiForgeryToken
    -0.42
    enterOuterAlt
    -0.42
     ModelExpression
    -0.42
    POSITIVE LOGITS
     hiding
    0.74
     shelter
    0.70
     esconder
    0.68
     hide
    0.67
    hiding
    0.66
     Hiding
    0.64
     refuge
    0.63
    shelter
    0.63
     shelters
    0.62
    Hiding
    0.61
    Act Density 0.061%

    No Known Activations