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

    Neuronpedia

    INDEX
    Explanations

    formal/technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Philosophy
    -0.07
     الناس
    -0.07
     플레이
    -0.07
    昭
    -0.07
     То
    -0.07
     oo
    -0.06
     drifting
    -0.06
     hills
    -0.06
     Сов
    -0.06
     suicides
    -0.06
    POSITIVE LOGITS
    州市
    0.07
    	login
    0.07
    login
    0.07
    搜
    0.06
    복
    0.06
     Everything
    0.06
     initializer
    0.06
    (components
    0.06
    _PER
    0.06
    /cc
    0.06
    Act Density 0.001%

    No Known Activations