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

    Neuronpedia

    INDEX
    Explanations

    equals signs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     orchest
    -0.07
    Sci
    -0.06
    整
    -0.06
     Tag
    -0.06
     leaks
    -0.06
     whats
    -0.06
    玻璃
    -0.06
     weil
    -0.06
     lil
    -0.06
    Ps
    -0.06
    POSITIVE LOGITS
     DISPATCH
    0.06
     ẩn
    0.06
    .BigDecimal
    0.06
    ервые
    0.06
    ROAD
    0.06
    Parm
    0.06
    \Column
    0.06
    unteer
    0.06
    	Created
    0.06
    òng
    0.06
    Act Density 0.142%

    No Known Activations