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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Spike
    -0.08
    -pr
    -0.07
     african
    -0.07
    radi
    -0.07
    喜
    -0.06
    GridView
    -0.06
    _after
    -0.06
     scaling
    -0.06
    ="#"><
    -0.06
    >*/↵
    -0.06
    POSITIVE LOGITS
    男性
    0.07
    pherical
    0.07
     तस
    0.06
     refuse
    0.06
    regnum
    0.06
     كس
    0.06
     Solution
    0.06
     outlier
    0.06
    landing
    0.06
    orrar
    0.06
    Act Density 0.025%

    No Known Activations