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

    Neuronpedia

    INDEX
    Explanations

    folding, serving, dressed, over

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     জল
    0.42
    鎂
    0.41
     ಕ್ಷೇತ್ರ
    0.40
    级别
    0.40
     ಮಂಗಳ
    0.40
    <unused28>
    0.39
    ْنَ
    0.39
    finaly
    0.39
    investissement
    0.38
     অতএব
    0.38
    POSITIVE LOGITS
     Java
    0.48
    荒
    0.46
     Clear
    0.39
    Java
    0.39
     Gl
    0.38
    0.38
     Ende
    0.37
     hat
    0.37
    pin
    0.37
     meter
    0.37
    Act Density 0.000%

    No Known Activations