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

    Neuronpedia

    INDEX
    Explanations

    drops

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Algorithm
    -0.06
     Sculpt
    -0.06
     Pal
    -0.06
    Physics
    -0.06
     traded
    -0.06
    Best
    -0.06
    birthday
    -0.06
     Plat
    -0.06
     Rifle
    -0.06
    ชาว
    -0.06
    POSITIVE LOGITS
    UsingEncoding
    0.08
    <<"
    0.07
    芳
    0.07
     여기
    0.07
     kayn
    0.06
     suggesting
    0.06
    _variables
    0.06
    '<
    0.06
    .dev
    0.06
     flashes
    0.06
    Act Density 0.003%

    No Known Activations