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

    Neuronpedia

    INDEX
    Explanations

    Proposed Advantages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     عشان
    0.55
    سطس
    0.52
     hapless
    0.51
     مشتقه
    0.48
     disallowed
    0.47
     shockingly
    0.47
    Ⴝ
    0.47
     shorthand
    0.46
     chuckle
    0.46
     someplace
    0.46
    POSITIVE LOGITS
     personnal
    0.94
     ressources
    0.94
     «
    0.93
     transfert
    0.91
     INSEE
    0.89
     Télé
    0.89
     environnement
    0.88
     autorisation
    0.86
     Ressources
    0.85
     exemple
    0.85
    Act Density 0.033%

    No Known Activations