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

    Neuronpedia

    INDEX
    Explanations

    rule or condition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     तकलीफ
    0.52
    颈
    0.50
    அ
    0.48
    Очень
    0.47
     Gopal
    0.46
     proportionately
    0.46
    んです
    0.45
    って
    0.45
    ري
    0.45
     голову
    0.44
    POSITIVE LOGITS
    den
    0.52
    ch
    0.48
     친
    0.46
    Teller
    0.46
    '}$
    0.44
    DEN
    0.43
    Password
    0.43
     DEN
    0.43
    charisma
    0.42
     यु
    0.42
    Act Density 0.000%

    No Known Activations