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

    Neuronpedia

    INDEX
    Explanations

    now

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Definitions
    -0.35
     definitions
    -0.32
    Definitions
    -0.30
     fortn
    -0.30
    dia
    -0.30
    definition
    -0.29
     dial
    -0.28
    Definition
    -0.27
     definition
    -0.27
     Definition
    -0.26
    POSITIVE LOGITS
     unset
    0.28
     sæ
    0.27
     thả
    0.26
    åĨį说
    0.26
    说çļĦè¯Ŀ
    0.26
    Wy
    0.26
    æīĭä¸Ĭ
    0.25
    éĹŃ
    0.25
    åı£æ°Ķ
    0.25
    æīĭä¸Ń
    0.25
    Act Density 0.001%

    No Known Activations