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

    Neuronpedia

    INDEX
    Explanations

    jokes about skeletons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     HEN
    0.35
     TECHNI
    0.35
    cnico
    0.34
     Fantasy
    0.34
    તર
    0.34
    RenderTarget
    0.33
     assum
    0.33
    嚀
    0.33
     pedagogy
    0.33
     SIG
    0.33
    POSITIVE LOGITS
    orthogonal
    0.40
     объеди
    0.39
     অন্তর
    0.39
    creation
    0.38
     archaeologists
    0.37
    Binding
    0.36
    binding
    0.36
    activated
    0.35
     gravitation
    0.34
    ฏิ
    0.34
    Act Density 0.002%

    No Known Activations