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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    DAQ
    -0.27
    ivant
    -0.26
    éĿľ
    -0.24
     ÑħозÑıй
    -0.24
     likeness
    -0.24
    好å¥ĩå¿ĥ
    -0.24
     envisioned
    -0.24
     slipped
    -0.23
    èĦijè¢ĭ
    -0.23
    DataProvider
    -0.23
    POSITIVE LOGITS
    rem
    0.28
    Meta
    0.28
    quam
    0.26
    _ib
    0.26
    Shar
    0.26
    Mac
    0.26
    å°¼æĸ¯
    0.25
    æĸľ
    0.24
    meta
    0.24
    wal
    0.24
    Act Density 0.135%

    No Known Activations