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

    Neuronpedia

    INDEX
    Explanations

    dispatching events

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Lies
    -0.09
     terl
    -0.08
    ymo
    -0.08
    ীম
    -0.08
     eliminated
    -0.08
     years
    -0.08
     literacy
    -0.08
    盈利
    -0.08
     prachtige
    -0.07
    /LICENSE
    -0.07
    POSITIVE LOGITS
     triggering
    0.12
    .trigger
    0.11
     भेज
    0.10
     stimulate
    0.10
     genü
    0.09
    	trigger
    0.09
    发送
    0.09
    刺激
    0.09
     stimulating
    0.09
     dispatched
    0.09
    Act Density 0.013%

    No Known Activations