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

    Neuronpedia

    INDEX
    Explanations

    <

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Johnson
    -0.07
     Johnson
    -0.07
     Batt
    -0.07
    .paint
    -0.07
    Custom
    -0.07
     ταιν
    -0.06
     oppon
    -0.06
     hilarious
    -0.06
    bold
    -0.06
    halten
    -0.06
    POSITIVE LOGITS
    ρία
    0.06
    _regs
    0.06
     //
↵
    0.06
    ISHED
    0.06
     chamber
    0.06
    ラック
    0.06
    nga
    0.06
     lease
    0.06
     diệt
    0.06
    \Auth
    0.06
    Act Density 0.007%

    No Known Activations