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

    Neuronpedia

    INDEX
    Explanations

    same or similar to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     మాత్రమే
    0.38
    ത്തിലും
    0.37
     spécifique
    0.37
     SULF
    0.37
     particolarmente
    0.36
     particularmente
    0.35
    㠱
    0.34
     частности
    0.34
     ಮಾತ್ರ
    0.34
    വിലെ
    0.33
    POSITIVE LOGITS
     same
    0.80
     samme
    0.71
    same
    0.68
    同じ
    0.68
     hetzelfde
    0.67
     ተመሳሳይ
    0.67
    Same
    0.64
     misma
    0.64
     একই
    0.62
     dezelfde
    0.62
    Act Density 0.029%

    No Known Activations