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

    Neuronpedia

    INDEX
    Explanations

    scientific nomenclature

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ے
    -0.07
    _tile
    -0.06
    .splitext
    -0.06
    (bean
    -0.06
     Silk
    -0.06
    [dir
    -0.06
    帶
    -0.06
     retirees
    -0.06
     pedestrians
    -0.06
    ทด
    -0.06
    POSITIVE LOGITS
    /accounts
    0.08
    "\
    0.07
    _permission
    0.07
     Validation
    0.07
     observational
    0.07
    starting
    0.06
    /account
    0.06
    lö
    0.06
    محافظ
    0.06
    äng
    0.06
    Act Density 0.010%

    No Known Activations