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

    Neuronpedia

    INDEX
    Explanations

    regulate, delete, deserve, assign, specify

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    p
    0.49
    у
    0.46
    м
    0.45
    ру
    0.44
    к
    0.44
    нес
    0.43
    не
    0.42
     LEGAL
    0.41
     Diagonal
    0.40
    лок
    0.39
    POSITIVE LOGITS
    Taiwan
    0.46
    Dig
    0.45
     novas
    0.45
    Xiao
    0.44
    colo
    0.44
    খী
    0.43
     quarry
    0.43
    Categoria
    0.43
    <unused1086>
    0.43
     помещения
    0.43
    Act Density 0.000%

    No Known Activations