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

    Neuronpedia

    INDEX
    Explanations

    Global

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     interface
    -0.06
     Minister
    -0.06
    	error
    -0.06
     pipelines
    -0.06
     senior
    -0.06
    мещ
    -0.06
    stractions
    -0.06
    STRING
    -0.06
    	trigger
    -0.06
     gran
    -0.06
    POSITIVE LOGITS
    ствия
    0.07
    عمال
    0.07
    _BT
    0.07
    都是
    0.06
    NSMutableArray
    0.06
    看到
    0.06
    회사
    0.06
    になり
    0.06
    OfWeek
    0.06
     strSQL
    0.06
    Act Density 0.000%

    No Known Activations