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

    Neuronpedia

    INDEX
    Explanations

    went

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Cop
    -0.07
     qué
    -0.06
    utation
    -0.06
     elit
    -0.06
    Degree
    -0.06
    _Mod
    -0.06
     serie
    -0.06
     Smith
    -0.06
     Abdul
    -0.06
    swer
    -0.06
    POSITIVE LOGITS
     wound
    0.07
    _cycles
    0.06
     혼
    0.06
     supermarket
    0.06
    992
    0.06
    167
    0.06
    bed
    0.06
    	description
    0.06
     desires
    0.06
    ریز
    0.06
    Act Density 0.000%

    No Known Activations