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

    Neuronpedia

    INDEX
    Explanations

    math symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     omas
    -0.07
    conc
    -0.07
     specific
    -0.07
     frog
    -0.07
    retch
    -0.06
     biến
    -0.06
    ざ
    -0.06
     Packages
    -0.06
    _trial
    -0.06
     tul
    -0.06
    POSITIVE LOGITS
     particip
    0.07
     Hoover
    0.07
    없는
    0.06
     Playlist
    0.06
     слож
    0.06
    (Enum
    0.06
     získal
    0.06
     Ziel
    0.06
    hopefully
    0.06
    wahl
    0.06
    Act Density 0.014%

    No Known Activations