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

    Neuronpedia

    INDEX
    Explanations

    law

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     recognizes
    -0.07
     hawk
    -0.07
    _restrict
    -0.07
    Downloads
    -0.07
    .Request
    -0.07
     hf
    -0.07
     permet
    -0.07
     load
    -0.07
    כלכ
    -0.07
     Lebanon
    -0.07
    POSITIVE LOGITS
     WTF
    0.08
     ruta
    0.07
     poking
    0.07
     waved
    0.07
    .getUrl
    0.07
    neath
    0.07
    :frame
    0.07
    estring
    0.07
     prt
    0.07
    Пр
    0.07
    Act Density 0.044%

    No Known Activations