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

    Neuronpedia

    INDEX
    Explanations

    LaTeX/programming commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    roasted
    0.47
    所谓的
    0.43
    கள்
    0.42
     کیے
    0.42
    DFS
    0.42
    များနှင့်
    0.42
    陟
    0.41
    ⏎
    0.40
     માં
    0.39
    మని
    0.39
    POSITIVE LOGITS
     setw
    0.50
     them
    0.47
     preparar
    0.46
     mr
    0.46
     fourteenth
    0.46
     THEM
    0.44
     MATERIAL
    0.43
     begin
    0.43
     establish
    0.43
     Them
    0.42
    Act Density 0.006%

    No Known Activations