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

    Neuronpedia

    INDEX
    Explanations

    function

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Vert
    -0.07
     cybersecurity
    -0.06
    ばかり
    -0.06
    Jean
    -0.06
     radius
    -0.06
    periences
    -0.06
     todo
    -0.06
     antenn
    -0.06
    .X
    -0.06
    企业
    -0.05
    POSITIVE LOGITS
     школи
    0.08
    .urls
    0.07
     incorporated
    0.07
    .Query
    0.07
     здоб
    0.07
    (initial
    0.07
    	Created
    0.07
     ald
    0.06
    еліг
    0.06
    .function
    0.06
    Act Density 0.005%

    No Known Activations