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

    Neuronpedia

    INDEX
    Explanations

    writing prompts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     maravilh
    0.51
     brilliantly
    0.49
     descripción
    0.47
     redução
    0.46
     compartilh
    0.45
     profundamente
    0.45
     descrizione
    0.45
     pérdida
    0.45
     resaltar
    0.45
     exploración
    0.44
    POSITIVE LOGITS
    R
    0.52
    NG
    0.52
    부
    0.50
    으로
    0.49
    Ι
    0.49
    GE
    0.47
    Μ
    0.47
    그
    0.46
     things
    0.46
    А
    0.46
    Act Density 0.000%

    No Known Activations