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

    Neuronpedia

    INDEX
    Explanations

    Warnings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    HN
    -0.07
     safeguard
    -0.06
    нак
    -0.06
     linger
    -0.06
     BELOW
    -0.06
    .available
    -0.06
    (hidden
    -0.06
    members
    -0.06
     أب
    -0.06
    unload
    -0.06
    POSITIVE LOGITS
    -ajax
    0.06
    ]+=
    0.06
     التد
    0.06
    .writeValue
    0.06
     breach
    0.06
    (worker
    0.06
     xhr
    0.06
    addChild
    0.06
     Зап
    0.06
     <<<
    0.06
    Act Density 0.014%

    No Known Activations