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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (c
    -0.07
     LZ
    -0.07
     honor
    -0.07
    ूक
    -0.06
    (th
    -0.06
    -rec
    -0.06
     switches
    -0.06
    larındaki
    -0.06
     Red
    -0.06
    contacts
    -0.06
    POSITIVE LOGITS
    تب
    0.08
     pancre
    0.07
    indo
    0.06
     характер
    0.06
    Category
    0.06
    .InputStreamReader
    0.06
    ollection
    0.06
     العامة
    0.06
    PARATOR
    0.06
     extrem
    0.06
    Act Density 0.045%

    No Known Activations