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

    Neuronpedia

    INDEX
    Explanations

    code comments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    atonin
    -0.07
     بودند
    -0.06
    amentals
    -0.06
    532
    -0.06
    ικό
    -0.06
     alternating
    -0.06
    ящих
    -0.06
     oblast
    -0.06
     vermek
    -0.06
    بال
    -0.06
    POSITIVE LOGITS
    -changing
    0.06
     typingsSlinky
    0.06
    37
    0.06
    �
    0.06
    dept
    0.06
     ideas
    0.06
     stable
    0.06
     conco
    0.05
    يان
    0.05
    .getStringExtra
    0.05
    Act Density 0.022%

    No Known Activations