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

    Neuronpedia

    INDEX
    Explanations

    length

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    iations
    -0.07
     allowing
    -0.07
     sacrificing
    -0.07
     $_
    -0.06
    看见
    -0.06
    ow
    -0.06
    ibly
    -0.06
    最新
    -0.06
     stacking
    -0.06
     Lớp
    -0.06
    POSITIVE LOGITS
    .Month
    0.07
     isempty
    0.07
    iyatı
    0.06
    ">*</
    0.06
    urable
    0.06
     dracon
    0.06
    -urlencoded
    0.06
    .Long
    0.06
    vlan
    0.06
    �
    0.06
    Act Density 0.003%

    No Known Activations