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

    Neuronpedia

    INDEX
    Explanations

    math calculations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ಕಂಡ
    -0.09
     tonos
    -0.09
    _errno
    -0.08
     Lieblings
    -0.08
     наход
    -0.08
    寻找
    -0.08
     Chow
    -0.07
     geleden
    -0.07
     신고
    -0.07
     കണ്ടെത്ത
    -0.07
    POSITIVE LOGITS
     surpass
    0.18
     exceeding
    0.14
     surpassed
    0.14
     exceeds
    0.13
     exceeded
    0.13
     insufficient
    0.13
     sufficient
    0.12
    Exceeded
    0.12
     exceed
    0.12
    adequ
    0.12
    Act Density 0.039%

    No Known Activations