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

    Neuronpedia

    INDEX
    Explanations

    shared

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     happened
    -0.08
    زا
    -0.07
    เธ
    -0.07
    _REFRESH
    -0.07
     Fé
    -0.07
    알
    -0.07
    Fcn
    -0.06
    ネット
    -0.06
    patibility
    -0.06
    circ
    -0.06
    POSITIVE LOGITS
     gaussian
    0.06
    [ix
    0.06
    _chars
    0.06
    (widget
    0.06
     Pitt
    0.06
    (owner
    0.06
     Craig
    0.06
    lásil
    0.06
    param
    0.06
     equ
    0.05
    Act Density 0.000%

    No Known Activations