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

    Neuronpedia

    INDEX
    Explanations

    helplines and crisis support

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ेंशियल
    0.42
     pły
    0.42
    वीय
    0.42
     రైతు
    0.42
     گز
    0.40
    âche
    0.40
    基督
    0.40
     варто
    0.40
    리면
    0.39
    ету
    0.39
    POSITIVE LOGITS
    n
    0.61
    d
    0.61
    in
    0.54
    i
    0.53
    y
    0.52
    min
    0.47
    e
    0.45
     inactivació
    0.45
    l
    0.44
    bold
    0.44
    Act Density 0.018%

    No Known Activations