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

    Neuronpedia

    INDEX
    Explanations

    quotation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Led
    -0.07
     από
    -0.06
    lr
    -0.06
     iid
    -0.06
     Luigi
    -0.06
    �
    -0.06
     Benton
    -0.06
     OnTrigger
    -0.06
     béné
    -0.06
     '*.
    -0.06
    POSITIVE LOGITS
    ricula
    0.07
    akat
    0.07
    imers
    0.06
     viên
    0.06
    uating
    0.06
    ......
    0.06
     mechanisms
    0.06
    _SIGN
    0.06
    ичної
    0.06
    ΗΝ
    0.06
    Act Density 0.006%

    No Known Activations