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

    Neuronpedia

    INDEX
    Explanations

    multiple languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     scratch
    -0.08
     convenience
    -0.08
    ンタ
    -0.07
     durfte
    -0.07
    ACITY
    -0.07
    省
    -0.07
    疾
    -0.07
     diet
    -0.07
     paljon
    -0.07
    _dash
    -0.07
    POSITIVE LOGITS
     оборудование
    0.10
     оборудования
    0.09
     실패
    0.09
     malfunction
    0.08
    .trigger
    0.08
    в
    0.08
     последствия
    0.08
    Shutdown
    0.08
     Grinding
    0.08
     зло
    0.08
    Act Density 0.000%

    No Known Activations