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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to hiding or concealment

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

    hide or conceal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AssemblyProduct
    -0.57
     endforeach
    -0.57
    󠁴
    -0.54
     للاسماء
    -0.52
    MessageOf
    -0.52
     useAppContext
    -0.50
     мәкал
    -0.49
    ➞
    -0.49
    PhysRev
    -0.48
    Soorten
    -0.48
    POSITIVE LOGITS
     hidden
    1.27
     Hidden
    1.18
     hide
    1.17
     hiding
    1.16
    Hidden
    1.09
     hides
    1.06
     concealed
    1.05
     Hide
    1.05
    hidden
    1.05
     conceal
    1.02
    Act Density 0.025%

    No Known Activations