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

    Neuronpedia

    INDEX
    Explanations

    references to law enforcement activities and associated legal actions

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

    contraband or narcotics found or hidden

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    exitRule
    -0.47
     enfans
    -0.47
    ใจ
    -0.43
    rinfo
    -0.42
     opcional
    -0.41
    opcional
    -0.41
    RefNanny
    -0.41
     cereales
    -0.40
     alimentación
    -0.40
    Consejos
    -0.40
    POSITIVE LOGITS
     hidden
    0.96
     concealed
    0.95
     hiding
    0.94
     Hidden
    0.88
     Hiding
    0.86
     hides
    0.84
     hide
    0.84
     hid
    0.82
     concealment
    0.81
     concealing
    0.81
    Act Density 0.107%

    No Known Activations