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

    Neuronpedia

    INDEX
    Explanations

    html head

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    am
    0.69
    an
    0.67
    the
    0.67
    A
    0.65
    one
    0.64
    S
    0.62
    m
    0.61
    +\
    0.60
     the
    0.60
    it
    0.60
    POSITIVE LOGITS
    窿
    0.83
     Câmara
    0.82
     suelos
    0.78
    силання
    0.77
    ⏫
    0.77
     кожного
    0.76
    ➧
    0.75
     aper
    0.75
     imageData
    0.74
    eiros
    0.74
    Act Density 0.010%

    No Known Activations