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

    Neuronpedia

    INDEX
    Explanations

    start or opening

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    뀐
    0.36
    rát
    0.36
    ClInclude
    0.34
    ਗ
    0.34
    ERRORTYPE
    0.32
    ensuremath
    0.32
    xcsche
    0.32
     tiế
    0.32
     лікар
    0.32
    Ꮥ
    0.32
    POSITIVE LOGITS
     initial
    2.56
     inicial
    2.30
    เริ่มต้น
    2.27
     iniziale
    2.23
    Initial
    2.20
    initial
    2.17
     Initial
    2.17
     시작
    2.17
     initiale
    2.17
    初始
    2.09
    Act Density 0.316%

    No Known Activations