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

    Neuronpedia

    INDEX
    Explanations

    financial advice

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Will
    0.39
     produces
    0.38
     కని
    0.38
    కా
    0.36
     restitution
    0.36
     exhibits
    0.35
    拟
    0.35
    usc
    0.35
    ritic
    0.35
    毎回
    0.35
    POSITIVE LOGITS
     invest
    0.52
    اون
    0.42
    投資
    0.42
    MOT
    0.40
     투자
    0.40
    任何
    0.39
    自由に
    0.39
     निवेश
    0.38
    wanted
    0.38
    ❿
    0.38
    Act Density 0.000%

    No Known Activations