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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    bergen
    -1.73
    berge
    -0.55
    Datuak
    -0.53
     stessi
    -0.51
    FormTagHelper
    -0.51
    MemoryWarning
    -0.49
     mismas
    -0.46
     hä
    -0.45
     mesma
    -0.45
     misma
    -0.45
    POSITIVE LOGITS
     متعلقه
    0.88
     pleaſure
    0.84
     "..\..\..\
    0.71
    ContentAsync
    0.71
     raiſ
    0.69
    spesies
    0.69
     myſelf
    0.68
    كتشاف
    0.67
     Philist
    0.64
     Efq
    0.64
    Act Density 0.133%

    No Known Activations