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

    Neuronpedia

    INDEX
    Explanations

    what does it mean

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     be
    1.84
    be
    1.54
     Be
    1.52
    Be
    1.46
     siano
    1.42
     tenha
    1.41
     aient
    1.39
     tenham
    1.36
     possano
    1.26
     possa
    1.25
    POSITIVE LOGITS
    おそらく
    0.83
     মূলত
    0.82
    גר
    0.80
     лишь
    0.77
    一个
    0.74
    ության
    0.73
     преимущественно
    0.72
    最多的
    0.72
     допол
    0.69
    最大的
    0.69
    Act Density 0.068%

    No Known Activations