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

    Neuronpedia

    INDEX
    Explanations

    simple project or role play

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     prépuce
    0.44
    ленным
    0.43
     сада
    0.43
    Firm
    0.43
    ября
    0.41
     dissati
    0.41
     Цу
    0.41
    덟
    0.41
    수한
    0.41
     долла
    0.40
    POSITIVE LOGITS
     right
    0.55
    مل
    0.48
     all
    0.46
    سر
    0.46
     fast
    0.45
     ranged
    0.45
     wind
    0.44
     which
    0.44
     Law
    0.44
     confirmed
    0.43
    Act Density 0.255%

    No Known Activations