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

    Neuronpedia

    INDEX
    Explanations

    from

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     happen
    -0.27
    æ³ī
    -0.26
    éĶº
    -0.24
    çļĦ强大
    -0.24
     teeth
    -0.24
     leak
    -0.24
    è¿ŀèĥľ
    -0.24
    entionPolicy
    -0.24
    åĵ²
    -0.24
    elly
    -0.24
    POSITIVE LOGITS
    bject
    0.27
    ussen
    0.25
     Erotic
    0.25
    ril
    0.25
    incer
    0.24
    éĩĩ访æŶ
    0.24
    çļĦæĸĩåŃĹ
    0.24
    EIF
    0.24
     Hir
    0.23
    课é¢ĺ
    0.23
    Act Density 12.149%

    No Known Activations