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

    Neuronpedia

    INDEX
    Explanations

    religious texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -proof
    -0.07
     posed
    -0.07
    盧
    -0.07
    nor
    -0.07
    疗
    -0.06
     for
    -0.06
    emain
    -0.06
     Universities
    -0.06
    -for
    -0.06
     Principal
    -0.06
    POSITIVE LOGITS
    行星
    0.08
    执导
    0.07
    *******↵
    0.07
    getDisplay
    0.07
     عبد
    0.07
    六个月
    0.07
    isFunction
    0.07
    DockControl
    0.07
    OutOfRange
    0.06
    ddl
    0.06
    Act Density 0.001%

    No Known Activations