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

    Neuronpedia

    INDEX
    Explanations

    omatic

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Interesting
    -0.08
     Intermediate
    -0.07
    Started
    -0.07
    Tonight
    -0.07
    	logging
    -0.07
     Apt
    -0.07
     fair
    -0.07
     price
    -0.07
    非要
    -0.07
     진행
    -0.07
    POSITIVE LOGITS
     seinen
    0.08
    马克
    0.07
    lyn
    0.07
    (ec
    0.07
    HEMA
    0.07
    拉斯
    0.07
    保罗
    0.07
    _AUTHOR
    0.07
    UTF
    0.06
    ural
    0.06
    Act Density 0.005%

    No Known Activations