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

    Neuronpedia

    INDEX
    Explanations

    Societal issues

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ä¸ĢåĪĢ
    -0.26
    nesty
    -0.25
    nde
    -0.24
     hype
    -0.24
    俳
    -0.24
     Kush
    -0.23
     Kom
    -0.23
    inati
    -0.23
    _ISO
    -0.23
    Od
    -0.23
    POSITIVE LOGITS
     dev
    0.28
    è¿
    0.27
    ":"","
    0.26
    éĶ¢
    0.25
    ä¸Ĭæµ·
    0.25
    elems
    0.25
     oc
    0.24
    åĵģç±»
    0.24
    ae
    0.24
    åĪĿä¸ī
    0.24
    Act Density 0.047%

    No Known Activations