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

    Neuronpedia

    INDEX
    Explanations

    end/termination

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     immediate
    -0.07
     Offset
    -0.07
     котор
    -0.07
    American
    -0.07
    lar
    -0.07
    sch
    -0.07
    _distance
    -0.07
     Atatürk
    -0.07
     Turk
    -0.07
    (integer
    -0.07
    POSITIVE LOGITS
     בס
    0.07
    itals
    0.07
     UPLOAD
    0.07
    Runner
    0.07
    UFACT
    0.07
    .ctrl
    0.07
    onyms
    0.07
    厌
    0.07
    ⇄
    0.06
    DrawerToggle
    0.06
    Act Density 0.142%

    No Known Activations