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

    Neuronpedia

    INDEX
    Explanations

    lists of words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     indented
    0.40
     overt
    0.37
     ranges
    0.36
     discre
    0.36
    ANI
    0.35
     Ire
    0.34
    xt
    0.34
     discret
    0.33
    bars
    0.33
     fastened
    0.33
    POSITIVE LOGITS
     آموزش
    0.49
     vacun
    0.47
    𒈪
    0.44
    াফিক
    0.42
     Teaching
    0.41
     присутствует
    0.41
     którzy
    0.41
    лкой
    0.40
     обучение
    0.39
    主催
    0.39
    Act Density 0.000%

    No Known Activations