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

    Neuronpedia

    INDEX
    Explanations

    409

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     iktidar
    -0.07
    izyon
    -0.07
    296
    -0.06
    嗎
    -0.06
    SetValue
    -0.06
    階
    -0.06
    营业
    -0.06
     gradient
    -0.06
    	Draw
    -0.06
    961
    -0.06
    POSITIVE LOGITS
    409
    0.32
    819
    0.17
    209
    0.13
    429
    0.09
    410
    0.08
     Residential
    0.08
     DAR
    0.07
    ("/")
    0.07
     bespoke
    0.07
    україн
    0.07
    Act Density 0.003%

    No Known Activations