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

    Neuronpedia

    INDEX
    Explanations

    biological experiments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ighted
    -0.30
     YE
    -0.27
    æ±Ł
    -0.26
     indefinitely
    -0.26
    åĨ¬
    -0.26
    åŀ¢
    -0.26
     ten
    -0.26
    sworth
    -0.25
    壽
    -0.25
    èģ²éŁ³
    -0.25
    POSITIVE LOGITS
    ник
    0.27
    æĮ¹
    0.25
    .setHeader
    0.25
     depressed
    0.24
    rev
    0.24
    RequestMapping
    0.23
    <head
    0.23
    éĦļ
    0.23
     growth
    0.23
     humble
    0.23
    Act Density 0.036%

    No Known Activations