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

    Neuronpedia

    INDEX
    Explanations

    current from food or electronics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     botón
    0.54
     acero
    0.49
     takım
    0.47
    חנו
    0.46
     méthode
    0.46
    回転
    0.45
    푼
    0.45
     Tahun
    0.45
     všetky
    0.45
     estándar
    0.44
    POSITIVE LOGITS
    i
    0.57
    nat
    0.56
    Nat
    0.50
    uti
    0.47
    Scandinavian
    0.46
     призна
    0.46
    eres
    0.45
    ira
    0.44
    nn
    0.44
     도
    0.44
    Act Density 0.003%

    No Known Activations