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

    Neuronpedia

    INDEX
    Explanations

    dialog labels followed by colon

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Nunes
    -0.10
     IOCTL
    -0.08
    )const
    -0.08
     Ange
    -0.08
     Wyn
    -0.08
    enus
    -0.08
     boh
    -0.08
    ëģĶ
    -0.08
    bitset
    -0.08
    947
    -0.08
    POSITIVE LOGITS
    :
    0.12
    $:
    0.11
    }:
    0.10
    æĽ°
    0.10
     :
    0.10
    #:
    0.10
     æĽ°
    0.09
    ]:
    0.09
     Brend
    0.09
    ､:
    0.09
    Act Density 0.153%

    No Known Activations