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

    Neuronpedia

    INDEX
    Explanations

    ranking

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    atthena
    0.36
    normalize
    0.36
    GoString
    0.36
    redient
    0.36
    俱
    0.36
    similarity
    0.35
     transg
    0.35
     similarity
    0.35
    ertid
    0.35
     Teich
    0.35
    POSITIVE LOGITS
     ranked
    0.67
     Ranked
    0.61
     ranking
    0.57
    ranked
    0.55
     sıral
    0.51
     Database
    0.50
    排
    0.50
    Ranking
    0.49
     Catalogue
    0.49
     RANK
    0.48
    Act Density 0.027%

    No Known Activations