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

    Neuronpedia

    INDEX
    Explanations

    technical concepts and jargon

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    built
    0.54
    ándolo
    0.51
     sprung
    0.51
    ́
    0.49
    ség
    0.48
    idão
    0.48
     другим
    0.47
     Боли
    0.47
    fall
    0.46
     built
    0.46
    POSITIVE LOGITS
     phosphat
    0.45
    ギ
    0.41
    ﻲ
    0.41
    СО
    0.40
    Kenny
    0.40
     erreur
    0.39
    त्या
    0.39
    MOTOR
    0.39
     immagin
    0.39
    初めて
    0.39
    Act Density 0.000%

    No Known Activations