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

    Neuronpedia

    INDEX
    Explanations

    git commands

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ilinear
    0.75
    𝔀
    0.74
    itory
    0.73
     damped
    0.71
    ności
    0.69
    venuti
    0.69
    槸
    0.68
    طف
    0.68
     enclosing
    0.68
    ცხ
    0.68
    POSITIVE LOGITS
    By
    0.79
    @
    0.77
     By
    0.74
     በፍ
    0.70
    Anon
    0.69
     About
    0.69
     Fung
    0.68
    кои
    0.68
    Instant
    0.68
     быстрее
    0.67
    Act Density 0.000%

    No Known Activations