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

    Neuronpedia

    INDEX
    Explanations

    projection

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	core
    -0.06
     inflate
    -0.06
    STRING
    -0.06
    nas
    -0.06
     인터넷
    -0.06
     termin
    -0.06
    112
    -0.06
    lements
    -0.06
     návště
    -0.06
    speech
    -0.06
    POSITIVE LOGITS
    ैय
    0.07
     Called
    0.07
    compiled
    0.07
     inclusive
    0.07
     Falling
    0.06
     fisheries
    0.06
     votes
    0.06
     lọc
    0.06
    CLUDING
    0.06
    пра
    0.06
    Act Density 0.003%

    No Known Activations