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

    Neuronpedia

    INDEX
    Explanations

    Medical statistics

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ώρα
    -0.07
     backstory
    -0.07
     allegiance
    -0.07
    资料
    -0.07
    _sample
    -0.06
    ulario
    -0.06
    Jwt
    -0.06
    lake
    -0.06
    小学
    -0.06
     곧
    -0.06
    POSITIVE LOGITS
     ім
    0.06
     Haut
    0.06
    .Light
    0.06
    wegian
    0.06
     conductor
    0.06
     uLocal
    0.06
     grop
    0.06
     Chase
    0.06
    quence
    0.06
    .ser
    0.06
    Act Density 0.061%

    No Known Activations