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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     درس
    -0.07
    /forms
    -0.07
    .WinForms
    -0.07
     eve
    -0.07
     अख
    -0.06
     horr
    -0.06
     multer
    -0.06
    賞
    -0.06
    _FIELDS
    -0.06
     tức
    -0.06
    POSITIVE LOGITS
    ipsis
    0.06
    £o
    0.06
     recurse
    0.06
    ikler
    0.06
     Warranty
    0.06
     Odyssey
    0.06
     scaling
    0.06
     кле
    0.06
    rips
    0.06
     agricultural
    0.06
    Act Density 0.009%

    No Known Activations