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

    Neuronpedia

    INDEX
    Explanations

    mechanics beneath

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    łem
    0.39
    iejęt
    0.38
     uve
    0.36
    ieben
    0.35
    ന്മ
    0.35
     showering
    0.35
    朝
    0.35
     currently
    0.34
    候
    0.34
    匁
    0.34
    POSITIVE LOGITS
     clase
    0.42
    닐
    0.41
    Ign
    0.40
     பழைய
    0.39
     IGN
    0.39
    Veter
    0.38
     சு
    0.38
     क्लास
    0.37
     كم
    0.37
     conver
    0.36
    Act Density 0.000%

    No Known Activations