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

    Neuronpedia

    INDEX
    Explanations

    latex comments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    公开
    0.40
     amelior
    0.38
     científico
    0.38
     scientists
    0.38
     Scient
    0.37
     kultury
    0.37
    কিন্তু
    0.37
    arbij
    0.37
     réunis
    0.37
    五个
    0.37
    POSITIVE LOGITS
    anam
    0.40
     mempel
    0.39
    పర్
    0.38
     Myl
    0.38
    ched
    0.37
     lid
    0.37
    ----------------
    0.37
    сын
    0.36
    ucus
    0.35
    lid
    0.35
    Act Density 0.000%

    No Known Activations