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

    Neuronpedia

    INDEX
    Explanations

    log message

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ডকুম
    0.40
    Illegal
    0.38
     ilegal
    0.38
     شخصی
    0.38
    गुजरात
    0.38
    手续
    0.37
     ምክንያ
    0.36
     சிகி
    0.36
     नकली
    0.36
     वैलेंट
    0.36
    POSITIVE LOGITS
     dudas
    0.45
     doubts
    0.43
     doubt
    0.42
    oubt
    0.39
    рию
    0.39
     aviation
    0.37
    ised
    0.35
     MBA
    0.35
    WO
    0.34
    MBA
    0.34
    Act Density 0.000%

    No Known Activations