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

    Neuronpedia

    INDEX
    Explanations

    block

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -hook
    -0.07
     correct
    -0.07
    	control
    -0.06
     spanking
    -0.06
    aphael
    -0.06
     Rap
    -0.06
     výrob
    -0.06
     StringUtil
    -0.06
    -toggler
    -0.06
     phép
    -0.06
    POSITIVE LOGITS
    contained
    0.07
     refuses
    0.06
    ЕР
    0.06
    ैर
    0.06
    LOS
    0.06
    Č
    0.06
    ↵↵↵↵↵↵↵↵↵↵↵↵
    0.06
     saddened
    0.06
    ilogue
    0.06
     modèle
    0.06
    Act Density 0.038%

    No Known Activations