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

    Neuronpedia

    INDEX
    Explanations

    explosive force

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bx
    0.43
     EXAMPLE
    0.41
     corollary
    0.40
     examples
    0.39
    erdings
    0.39
     കഥ
    0.38
     lit
    0.38
    unnumbered
    0.37
     ટ્ર
    0.37
     ውስ
    0.37
    POSITIVE LOGITS
    손
    0.46
    Prog
    0.43
    ௐ
    0.40
    ArgsEnv
    0.39
    -%
    0.39
    THRESH
    0.38
    લું
    0.38
    Clear
    0.38
    Сегодня
    0.38
     EventArgs
    0.37
    Act Density 0.001%

    No Known Activations