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

    Neuronpedia

    INDEX
    Explanations

    Common short words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nói
    -0.07
    。你
    -0.07
     potom
    -0.06
    prepared
    -0.06
    represented
    -0.06
    iciel
    -0.06
    itud
    -0.06
     Uni
    -0.06
     bathrooms
    -0.06
    Tuple
    -0.06
    POSITIVE LOGITS
    });
↵
    0.07
    Guess
    0.06
     Jude
    0.06
     attire
    0.06
    enan
    0.06
    isLoading
    0.06
    입
    0.06
    	Entity
    0.06
    _ticket
    0.06
     Diagram
    0.06
    Act Density 0.028%

    No Known Activations