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

    Neuronpedia

    INDEX
    Explanations

    correcting, completing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     свя
    -0.08
    �
    -0.07
    يو
    -0.07
    そこ
    -0.07
     Gian
    -0.06
    �
    -0.06
     BlockPos
    -0.06
    طه
    -0.06
    二人
    -0.06
    lope
    -0.06
    POSITIVE LOGITS
     recognised
    0.07
    -net
    0.06
     prosecution
    0.06
     classrooms
    0.06
    .openqa
    0.06
    ":{"
    0.06
    Originally
    0.06
     getResources
    0.06
     resett
    0.05
     relationships
    0.05
    Act Density 0.003%

    No Known Activations