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

    Neuronpedia

    INDEX
    Explanations

    event names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _ack
    -0.08
    flux
    -0.07
    廠
    -0.07
     先
    -0.07
    	opt
    -0.07
    етич
    -0.07
     کود
    -0.06
    彦
    -0.06
     Resorts
    -0.06
     polynomial
    -0.06
    POSITIVE LOGITS
    pr
    0.07
     troubled
    0.06
     Nov
    0.06
     cumpl
    0.06
     Feb
    0.06
     géné
    0.06
     Apr
    0.06
    utton
    0.06
    ařilo
    0.06
    nton
    0.05
    Act Density 0.082%

    No Known Activations