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

    Neuronpedia

    INDEX
    Explanations

    Instructions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    แสดง
    -0.07
     dışarı
    -0.06
    xA
    -0.06
     #@
    -0.06
    Nodes
    -0.06
    ける
    -0.06
    892
    -0.06
    자료
    -0.06
     �
    -0.06
    :set
    -0.06
    POSITIVE LOGITS
    .publisher
    0.07
    .Invariant
    0.07
    ?=.*
    0.06
    ihan
    0.06
     ideological
    0.06
     Hon
    0.06
     ABOVE
    0.06
    addClass
    0.06
    assessment
    0.06
     kodu
    0.06
    Act Density 0.215%

    No Known Activations