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

    Neuronpedia

    INDEX
    Explanations

    function definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    områ
    0.31
    ุ
    0.30
    ſ
    0.30
    artigen
    0.30
    Für
    0.29
    didn
    0.29
     angesehen
    0.29
    件事
    0.29
     कपल
    0.29
    芘
    0.28
    POSITIVE LOGITS
     get
    0.50
     make
    0.44
     create
    0.44
     encode
    0.40
     _
    0.38
     parse
    0.38
     compute
    0.38
     build
    0.38
     convert
    0.37
     maximize
    0.37
    Act Density 0.077%

    No Known Activations