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

    Neuronpedia

    INDEX
    Explanations

    NET, Mechanical, Beach, Original

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    نت
    0.49
     فارسی
    0.48
    halt
    0.46
    داث
    0.43
     nto
    0.43
     annum
    0.43
     anul
    0.42
     reparar
    0.42
     doctrina
    0.42
    निर्भर
    0.41
    POSITIVE LOGITS
     यश
    0.48
     weigh
    0.45
    urezza
    0.45
     checkpoint
    0.41
     स्ट
    0.40
    uleux
    0.40
     ఇటీవల
    0.40
    ﭘ
    0.39
     चोप
    0.39
    éticos
    0.39
    Act Density 0.008%

    No Known Activations