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

    Neuronpedia

    INDEX
    Explanations

    spending money

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Aurora
    -0.07
    Ơ
    -0.07
     rough
    -0.06
    _restart
    -0.06
    Thông
    -0.06
     Petit
    -0.06
    /aws
    -0.06
    _internal
    -0.06
    ential
    -0.06
     Quint
    -0.06
    POSITIVE LOGITS
    캐
    0.07
     vowels
    0.07
    をする
    0.06
     glEnable
    0.06
     isError
    0.06
     flask
    0.06
     garlic
    0.06
    CEEDED
    0.06
    +h
    0.06
     odio
    0.06
    Act Density 0.013%

    No Known Activations