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

    Neuronpedia

    INDEX
    Explanations

    various strings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pe
    -0.33
    омн
    -0.26
     Tra
    -0.26
    Disallow
    -0.26
    pe
    -0.26
    Peer
    -0.26
    alf
    -0.26
    åĮ
    -0.26
    atica
    -0.26
    Tra
    -0.25
    POSITIVE LOGITS
    MOST
    0.29
    _lengths
    0.28
     reass
    0.27
    åĩºæ¸¸
    0.27
     Saunders
    0.26
    èĤĮèĤī
    0.26
    -length
    0.26
    她说
    0.26
    unde
    0.25
    æ¯Ķäºļ
    0.24
    Act Density 0.001%

    No Known Activations