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

    Neuronpedia

    INDEX
    Explanations

    unbeatable

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    lø
    0.52
     cardiaque
    0.46
     energies
    0.46
    spring
    0.45
     équ
    0.44
     imparting
    0.43
     αλλά
    0.42
     écl
    0.42
     έ
    0.42
     adju
    0.42
    POSITIVE LOGITS
    이브
    0.46
     mattress
    0.45
     পরাজ
    0.44
     childish
    0.42
     islamic
    0.41
     Mattress
    0.41
     unbeatable
    0.41
    ODI
    0.40
    icycle
    0.40
    ндекс
    0.40
    Act Density 0.000%

    No Known Activations