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

    Neuronpedia

    INDEX
    Explanations

    build

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ampler
    -0.06
     часом
    -0.06
     moons
    -0.06
    Statics
    -0.06
    遺
    -0.06
    تش
    -0.06
     klass
    -0.06
    .Stat
    -0.06
    -legged
    -0.06
    (op
    -0.06
    POSITIVE LOGITS
     Combination
    0.07
     youre
    0.07
    ruby
    0.06
    erm
    0.06
     qa
    0.06
     IRA
    0.06
    "—
    0.06
    在线阅读
    0.06
     december
    0.06
    .xlsx
    0.06
    Act Density 0.003%

    No Known Activations