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

    Neuronpedia

    INDEX
    Explanations

    Malkavian, lmgrd, down

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     프로세
    0.52
    Descrição
    0.50
     צ
    0.49
    국
    0.49
     ר
    0.48
    의
    0.48
    당
    0.47
     계
    0.47
    بعد
    0.47
    questao
    0.47
    POSITIVE LOGITS
    et
    0.62
    on
    0.60
    or
    0.54
    o
    0.54
    ppard
    0.53
    y
    0.53
    сен
    0.50
    άρ
    0.50
    та
    0.49
    િય
    0.47
    Act Density 0.000%

    No Known Activations