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

    Neuronpedia

    INDEX
    Explanations

    require

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     SPDX
    -0.06
    SB
    -0.06
     Hồng
    -0.06
    �
    -0.06
    .container
    -0.06
     orbs
    -0.06
    _flip
    -0.06
     openid
    -0.06
    nech
    -0.06
     peaceful
    -0.06
    POSITIVE LOGITS
     conocer
    0.07
     cheats
    0.07
    anne
    0.06
     %↵↵
    0.06
     ケ
    0.06
     recruitment
    0.06
    řaz
    0.06
     Flood
    0.06
    лося
    0.06
     essential
    0.06
    Act Density 0.003%

    No Known Activations