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

    Neuronpedia

    INDEX
    Explanations

    Research data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Drivers
    -0.07
    ule
    -0.07
    	Query
    -0.07
     request
    -0.07
     predictors
    -0.07
     horn
    -0.07
    Query
    -0.06
     job
    -0.06
     emphasis
    -0.06
     Wait
    -0.06
    POSITIVE LOGITS
     draggable
    0.07
     stringstream
    0.06
     производства
    0.06
    ekl
    0.06
     创建
    0.06
    @dynamic
    0.06
    äß
    0.06
    (seq
    0.06
    еріг
    0.06
    TEE
    0.06
    Act Density 0.333%

    No Known Activations