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

    Neuronpedia

    INDEX
    Explanations

    place names and descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ί
    0.87
    ado
    0.83
    deki
    0.83
    they
    0.73
    owy
    0.71
    ين
    0.70
     conseguiu
    0.68
    í
    0.68
     construye
    0.68
    ной
    0.67
    POSITIVE LOGITS
     I
    0.69
     pch
    0.64
     an
    0.63
     velocities
    0.63
     ribbons
    0.62
     the
    0.61
    ING
    0.60
     increases
    0.60
    s
    0.59
     Inst
    0.59
    Act Density 0.030%

    No Known Activations