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

    Neuronpedia

    INDEX
    Explanations

    ://

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    law
    -0.07
    업체
    -0.07
    stal
    -0.07
     halde
    -0.07
    (wp
    -0.07
    rightarrow
    -0.07
    dict
    -0.07
     feminine
    -0.07
    Rs
    -0.06
    sep
    -0.06
    POSITIVE LOGITS
    getAs
    0.06
     AVG
    0.06
     صفحه
    0.06
    减
    0.06
     Price
    0.06
     sagte
    0.06
    Feature
    0.06
    $',
    0.06
     Plug
    0.05
     tuned
    0.05
    Act Density 0.034%

    No Known Activations