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

    Neuronpedia

    INDEX
    Explanations

    un

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	array
    -0.09
    	unsigned
    -0.07
     Mime
    -0.07
    记忆力
    -0.07
    pac
    -0.07
     implode
    -0.07
    ertools
    -0.06
    _every
    -0.06
    doors
    -0.06
    _ctor
    -0.06
    POSITIVE LOGITS
    -pos
    0.08
    salary
    0.08
     postal
    0.07
    РО
    0.07
     observe
    0.07
    င
    0.07
    requ
    0.07
    ✚
    0.07
     Stap
    0.07
    Β
    0.07
    Act Density 0.002%

    No Known Activations