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

    Neuronpedia

    INDEX
    Explanations

    intended

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Lim
    -0.07
     productos
    -0.07
    <B
    -0.07
     borrow
    -0.06
    vající
    -0.06
    �
    -0.06
     disjoint
    -0.06
     Další
    -0.06
     nin
    -0.06
     HWND
    -0.06
    POSITIVE LOGITS
     revolution
    0.06
    (InputStream
    0.06
    (hw
    0.06
    emploi
    0.06
    (userid
    0.06
    _↵↵
    0.06
     expenditures
    0.06
    (ticket
    0.06
    苦
    0.06
     ethic
    0.06
    Act Density 0.003%

    No Known Activations