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

    Neuronpedia

    INDEX
    Explanations

    `currently` or `approach`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    最適な
    0.40
    కుంట
    0.39
     ይችላሉ
    0.39
    Lol
    0.37
     Erkennt
    0.36
    此前
    0.36
     بودند
    0.36
     Literally
    0.36
     غم
    0.36
    νες
    0.36
    POSITIVE LOGITS
    ләү
    0.44
     लेख
    0.37
     approche
    0.37
     gout
    0.37
     approach
    0.37
    ปัจจุบัน
    0.37
     evolving
    0.37
     tempo
    0.36
    ncia
    0.36
     CURRENT
    0.35
    Act Density 0.000%

    No Known Activations