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

    Neuronpedia

    INDEX
    Explanations

    situations involving eavesdropping or overhearing conversations

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

    overhearing conversations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GraphicsUnit
    -0.44
     الرياضيه
    -0.39
    WebKit
    -0.39
    mologie
    -0.36
    setImageBitmap
    -0.36
     CGPoint
    -0.36
     photographic
    -0.35
    StatusCodes
    -0.35
     Sagan
    -0.35
     Haag
    -0.35
    POSITIVE LOGITS
     heard
    0.82
     mendengar
    0.81
     overheard
    0.79
     hears
    0.78
     escuchar
    0.77
     hearing
    0.77
     hear
    0.76
     صوتيه
    0.75
     listened
    0.73
     Hearing
    0.72
    Act Density 0.036%

    No Known Activations