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

    Neuronpedia

    INDEX
    Explanations

    best fit

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    чите
    0.39
     Beispiel
    0.39
     cleanly
    0.39
    流行的
    0.38
    ைகளின்
    0.38
    酋
    0.38
     vollständ
    0.38
     vollständig
    0.38
    wenn
    0.38
     korrekt
    0.37
    POSITIVE LOGITS
     amount
    0.40
     one
    0.40
     otp
    0.39
     anum
    0.39
     onem
    0.39
     option
    0.38
    ﺮ
    0.37
    なお
    0.36
     дополни
    0.36
     עבור
    0.36
    Act Density 0.028%

    No Known Activations