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

    Neuronpedia

    INDEX
    Explanations

    analog circuits

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     etik
    0.46
     FIELDS
    0.46
     nebude
    0.44
     priorit
    0.42
     Relationships
    0.41
     முதல்வர்
    0.41
    హా
    0.41
    ন
    0.41
    াসা
    0.40
     sympathies
    0.40
    POSITIVE LOGITS
     дет
    0.55
     нео
    0.47
    0.46
     зна
    0.46
    )});
    0.45
     защи
    0.45
     сле
    0.44
     тро
    0.44
    0.44
     Дет
    0.44
    Act Density 0.002%

    No Known Activations