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

    Neuronpedia

    INDEX
    Explanations

    Period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     spotřeb
    -0.07
    .students
    -0.06
     vlak
    -0.06
     tránh
    -0.06
     compt
    -0.06
    样
    -0.06
     Sachs
    -0.06
    -lite
    -0.06
    ΙΤ
    -0.06
    λό
    -0.06
    POSITIVE LOGITS
     Salv
    0.07
     Alic
    0.06
    .ALIGN
    0.06
     align
    0.06
    	align
    0.06
    しま
    0.06
    ((&___
    0.06
     tough
    0.06
    ("//
    0.06
    ош
    0.06
    Act Density 0.072%

    No Known Activations