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

    Neuronpedia

    INDEX
    Explanations

    SP

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ILE
    -0.09
    endphp
    -0.07
     midpoint
    -0.07
    空间
    -0.06
    وث
    -0.06
    くれた
    -0.06
    销
    -0.06
    ile
    -0.06
     unsere
    -0.06
    PROJECT
    -0.06
    POSITIVE LOGITS
    .ToList
    0.07
    thread
    0.07
     della
    0.06
    .Re
    0.06
     affair
    0.06
    _regression
    0.06
     physicists
    0.06
    .exceptions
    0.06
     booty
    0.06
     whore
    0.06
    Act Density 0.122%

    No Known Activations