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

    Neuronpedia

    INDEX
    Explanations

    ):

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Marvel
    -0.07
     Tesla
    -0.07
    NASA
    -0.06
     Motorola
    -0.06
     Hindu
    -0.06
     Appeals
    -0.06
     jeder
    -0.06
    	me
    -0.06
    够
    -0.06
     IQ
    -0.06
    POSITIVE LOGITS
     jumped
    0.07
     heartbreaking
    0.06
    ">{{$
    0.06
     deutschland
    0.06
    -Identifier
    0.06
    UNIT
    0.06
    _excerpt
    0.06
    今年
    0.06
     controlling
    0.06
    ITTLE
    0.06
    Act Density 0.021%

    No Known Activations