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

    Neuronpedia

    INDEX
    Explanations

    000

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     idiot
    -0.07
     awful
    -0.06
    (Page
    -0.06
    毎
    -0.06
    Todo
    -0.06
     Loch
    -0.06
     Txt
    -0.06
    “But
    -0.06
     Tray
    -0.06
     hardwood
    -0.06
    POSITIVE LOGITS
    .С
    0.07
    GenericType
    0.07
     Stanton
    0.07
     Copenhagen
    0.07
    krv
    0.07
    езульт
    0.07
    らく
    0.07
    .–
    0.07
    _rates
    0.07
    __,↵
    0.06
    Act Density 0.016%

    No Known Activations