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

    Neuronpedia

    INDEX
    Explanations

    到

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     furl
    -0.07
     cohorts
    -0.07
     cue
    -0.07
    	statement
    -0.07
     governing
    -0.07
     paragraph
    -0.07
     chips
    -0.07
     sentence
    -0.07
    Outbound
    -0.07
     cohort
    -0.07
    POSITIVE LOGITS
     converge
    0.12
     convergence
    0.11
    _final
    0.11
     النهائي
    0.11
     conver
    0.11
     reached
    0.11
     Final
    0.11
     đạt
    0.10
     erreicht
    0.10
     obtained
    0.10
    Act Density 0.011%

    No Known Activations