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

    Neuronpedia

    INDEX
    Explanations

    specific numbers and words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     múltiples
    0.56
     lectores
    0.52
    ino
    0.51
     An
    0.51
     internationales
    0.50
     geométricas
    0.49
     consommateurs
    0.49
    inam
    0.48
    orie
    0.48
     filles
    0.47
    POSITIVE LOGITS
    ろ
    0.46
    ב
    0.44
    אל
    0.44
    Bạn
    0.43
    אס
    0.43
    צ
    0.43
    בר
    0.42
    さ
    0.42
    Vr
    0.42
    פ
    0.41
    Act Density 0.000%

    No Known Activations