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

    Neuronpedia

    INDEX
    Explanations

    chemical reactions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    uma
    -0.07
     대해
    -0.07
    ัง
    -0.07
    =========
    -0.06
    fa
    -0.06
    usters
    -0.06
    RDD
    -0.06
    �로
    -0.06
    adia
    -0.06
     спри
    -0.06
    POSITIVE LOGITS
     emp
    0.07
     يج
    0.07
    	p
    0.07
    _regularizer
    0.06
    .APPLICATION
    0.06
    	config
    0.06
    ्बर
    0.06
    direction
    0.06
    .level
    0.06
     configuration
    0.06
    Act Density 0.077%

    No Known Activations