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

    Neuronpedia

    INDEX
    Explanations

    tests and experiments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     হল
    -0.08
     হলো
    -0.08
     म्हणजे
    -0.08
    ाऊ
    -0.08
    avag
    -0.07
    'appar
    -0.07
     does
    -0.07
     stands
    -0.07
     Bursa
    -0.07
    angezien
    -0.07
    POSITIVE LOGITS
     disguised
    0.11
    ached
    0.08
    某
    0.08
     કંઈ
    0.08
     evolved
    0.08
    ACHED
    0.08
    _REQUIRED
    0.08
     secretly
    0.08
     disguise
    0.08
    atee
    0.08
    Act Density 0.039%

    No Known Activations