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

    Neuronpedia

    INDEX
    Explanations

    foreign language or script

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Analyse
    0.52
     To
    0.45
     +(
    0.44
     wyniku
    0.44
    ل
    0.43
    analyse
    0.43
     Advice
    0.42
    стви
    0.42
     to
    0.41
     onto
    0.41
    POSITIVE LOGITS
    ಟ್ರ
    0.52
     алюми
    0.48
    addington
    0.47
     regaining
    0.47
    measuredangle
    0.46
     ビタミン
    0.45
     drooping
    0.45
     преступ
    0.44
     estrem
    0.44
     sputum
    0.44
    Act Density 0.001%

    No Known Activations