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

    Neuronpedia

    INDEX
    Explanations

    mixed languages and formats

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     själv
    0.60
     selv
    0.60
    Andre
    0.55
     selbst
    0.55
    اند
    0.54
    Sel
    0.53
    自
    0.52
     Ander
    0.51
     само
    0.50
     Andre
    0.50
    POSITIVE LOGITS
     lad
    0.52
     Lad
    0.50
    Lad
    0.42
     icin
    0.39
    ơm
    0.36
    סף
    0.36
    felt
    0.36
     purchases
    0.36
     fork
    0.36
     oor
    0.35
    Act Density 0.000%

    No Known Activations