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

    Neuronpedia

    INDEX
    Explanations

    foreign and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     general
    0.48
    0.47
    다면
    0.45
    s
    0.44
    able
    0.44
     causal
    0.44
     w
    0.43
    es
    0.42
     dominant
    0.42
     mang
    0.42
    POSITIVE LOGITS
     сайта
    0.83
    lensFlare
    0.80
    До
    0.80
    количество
    0.80
    zynarod
    0.80
    Issledovatel
    0.79
    aparikkh
    0.77
    goài
    0.77
    ф
    0.77
    kében
    0.76
    Act Density 0.139%

    No Known Activations