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

    Neuronpedia

    INDEX
    Explanations

    chapters and bad anatomy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ﻟ
    0.53
    彼の
    0.45
    गण
    0.44
    он
    0.44
     его
    0.44
     नेताओं
    0.43
     त्याच्या
    0.43
    াব্য
    0.43
    Minneapolis
    0.42
     його
    0.42
    POSITIVE LOGITS
     Schr
    0.52
     Rod
    0.46
     actively
    0.46
     comando
    0.46
     đỡ
    0.45
     inn
    0.44
    中医
    0.44
    us
    0.44
     Ai
    0.43
     An
    0.43
    Act Density 0.001%

    No Known Activations