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

    Neuronpedia

    INDEX
    Explanations

    Arial font family

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bộ
    0.81
     ujar
    0.75
     vetor
    0.66
    sterdam
    0.64
    ット
    0.62
    Ϫ
    0.60
    交易所
    0.60
     posición
    0.60
     anglès
    0.59
     clín
    0.59
    POSITIVE LOGITS
    ে
    0.61
    на
    0.60
    in
    0.57
    an
    0.55
    or
    0.54
    m
    0.53
    ви
    0.53
    ми
    0.53
     ж
    0.53
    トゥ
    0.53
    Act Density 0.002%

    No Known Activations