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

    Neuronpedia

    INDEX
    Explanations

    working through problems

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    setRequestHeader
    1.36
     godina
    1.34
    ্যোগ
    1.33
     sorties
    1.30
     учи
    1.27
     fwrite
    1.27
    giờ
    1.26
    ина
    1.26
     Уни
    1.23
     piracy
    1.20
    POSITIVE LOGITS
    n
    1.63
     mulighed
    1.29
    ر
    1.26
    er
    1.25
    Deterministic
    1.23
    एक्स
    1.16
    之間的
    1.16
    p
    1.15
    ె
    1.15
    Tuple
    1.12
    Act Density 0.000%

    No Known Activations