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

    Neuronpedia

    INDEX
    Explanations

    True

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ございます
    -0.06
     возника
    -0.06
    �
    -0.06
    employ
    -0.06
    pcl
    -0.06
    .**************↵
    -0.06
    productive
    -0.06
    	foreach
    -0.06
    ulsive
    -0.06
     οι
    -0.06
    POSITIVE LOGITS
     buzz
    0.07
     tuna
    0.07
    rze
    0.07
     paperback
    0.06
    _bn
    0.06
    ож
    0.06
    )(__
    0.06
     Frozen
    0.06
    طح
    0.06
    reffen
    0.06
    Act Density 0.008%

    No Known Activations