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

    Neuronpedia

    INDEX
    Explanations

    Specifying different species

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     internal
    -0.06
    Air
    -0.06
     hooks
    -0.06
     eight
    -0.06
    host
    -0.06
    اورزی
    -0.06
     Uz
    -0.06
    8
    -0.06
     Mental
    -0.06
     сопров
    -0.06
    POSITIVE LOGITS
     specials
    0.07
    _demo
    0.06
    Demo
    0.06
    _files
    0.06
    umen
    0.06
    について
    0.06
    	else
    0.06
     "))↵
    0.06
    "label
    0.06
    uous
    0.06
    Act Density 0.537%

    No Known Activations