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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     而
    -0.07
     XOR
    -0.07
    ’l
    -0.07
    ル
    -0.07
    احت
    -0.07
     strtolower
    -0.07
    树
    -0.07
    03
    -0.07
     terrible
    -0.06
    抜
    -0.06
    POSITIVE LOGITS
     przypad
    0.06
     вас
    0.06
    로서
    0.06
     Ket
    0.06
     cheek
    0.06
    egree
    0.06
    InterfaceOrientation
    0.06
    Activate
    0.06
     caso
    0.06
    .destination
    0.06
    Act Density 0.017%

    No Known Activations