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

    Neuronpedia

    INDEX
    Explanations

    conditional statements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Directed
    -0.06
    	opt
    -0.06
    Exiting
    -0.06
    _index
    -0.06
     contexts
    -0.06
     검색
    -0.06
    MAS
    -0.06
     или
    -0.06
     CLIENT
    -0.06
    .orm
    -0.06
    POSITIVE LOGITS
    (goal
    0.07
    -Za
    0.07
    �
    0.07
    тора
    0.06
    ，↵↵
    0.06
    ange
    0.06
    *h
    0.06
    (angle
    0.06
    ]}↵
    0.06
    ]):↵
    0.06
    Act Density 0.075%

    No Known Activations