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

    Neuronpedia

    INDEX
    Explanations

    Informational/conversational text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    щим
    -0.07
    �
    -0.07
    Trim
    -0.07
    _iter
    -0.06
    .simple
    -0.06
     vyj
    -0.06
    \Route
    -0.06
     cider
    -0.06
    919
    -0.06
     cheating
    -0.06
    POSITIVE LOGITS
    	iNdEx
    0.06
    521
    0.06
     Insecta
    0.06
    (↵↵
    0.06
    Оп
    0.06
    "?↵↵
    0.06
    affe
    0.06
    ={"
    0.06
     μια
    0.05
     Оп
    0.05
    Act Density 0.054%

    No Known Activations