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

    Neuronpedia

    INDEX
    Explanations

    Me

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    kule
    0.77
     découvre
    0.76
    㖦
    0.75
     оригі
    0.75
    ﾏ
    0.74
    itä
    0.73
    жек
    0.72
    imha
    0.72
    álně
    0.72
    рија
    0.72
    POSITIVE LOGITS
     сон
    0.81
     BMI
    0.78
     qualified
    0.78
     breeze
    0.78
     shoots
    0.76
     qualification
    0.74
    剂
    0.73
    BMI
    0.71
     wickets
    0.70
    F
    0.70
    Act Density 0.000%

    No Known Activations