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

    Neuronpedia

    INDEX
    Explanations

    removal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     shortages
    -0.07
     επισ
    -0.07
     миров
    -0.06
    Supply
    -0.06
     mieux
    -0.06
    712
    -0.06
     delaying
    -0.06
    科技
    -0.06
     distract
    -0.06
     denom
    -0.06
    POSITIVE LOGITS
    _TEAM
    0.06
    )<
    0.06
    modifier
    0.06
     dipl
    0.06
    .right
    0.06
    .getBoolean
    0.06
    ัมพ
    0.06
    ortho
    0.06
    hwnd
    0.06
    เช
    0.06
    Act Density 0.135%

    No Known Activations