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

    Neuronpedia

    INDEX
    Explanations

    code and technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Shapes
    -0.06
     研
    -0.06
     наруж
    -0.06
     DOS
    -0.06
     Param
    -0.06
    anker
    -0.06
    uniacid
    -0.06
     открыт
    -0.06
     wherein
    -0.06
    playlist
    -0.06
    POSITIVE LOGITS
    weapons
    0.08
     ｲ
    0.07
    充
    0.06
     Apple
    0.06
     textures
    0.06
     manually
    0.06
    equip
    0.06
    ักก
    0.06
    omat
    0.06
    /exec
    0.06
    Act Density 0.000%

    No Known Activations