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

    Neuronpedia

    INDEX
    Explanations

    foreign languages and specific entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    urangan
    0.26
     Orton
    0.25
    merich
    0.25
    gehend
    0.24
    eway
    0.24
    }");
    0.24
    leq
    0.24
     orator
    0.24
    ldigt
    0.23
    phalodes
    0.23
    POSITIVE LOGITS
    0.26
    소
    0.25
    ፖ
    0.24
     Toyota
    0.24
     ги
    0.24
    政府
    0.24
    Ро
    0.24
    ใน
    0.24
     Binance
    0.23
     είναι
    0.23
    Act Density 0.000%

    No Known Activations