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

    Neuronpedia

    INDEX
    Explanations

    behavior

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ete
    -0.07
    Combat
    -0.06
    .Lo
    -0.06
    .FixedSingle
    -0.06
    ć
    -0.06
     электрон
    -0.06
    iyesi
    -0.06
    _fee
    -0.06
    ";↵↵↵
    -0.06
    uala
    -0.06
    POSITIVE LOGITS
     reserved
    0.07
     Array
    0.07
     violently
    0.07
    _PASSWORD
    0.07
     Hod
    0.07
    otted
    0.07
     (~(
    0.06
     ample
    0.06
     podem
    0.06
     topics
    0.06
    Act Density 0.019%

    No Known Activations