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

    Neuronpedia

    INDEX
    Explanations

    families

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Continental
    -0.07
    (vec
    -0.06
     :/
    -0.06
    ,
↵
    -0.06
     conservatism
    -0.06
     yn
    -0.06
    -In
    -0.06
    <Edge
    -0.06
     Chop
    -0.06
    /to
    -0.06
    POSITIVE LOGITS
    interface
    0.07
    为空
    0.06
    validate
    0.06
    ΟΦ
    0.06
     difficulty
    0.06
    |wx
    0.06
    .random
    0.06
    _uploaded
    0.06
    namespace
    0.06
    ��态
    0.06
    Act Density 0.001%

    No Known Activations