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

    Neuronpedia

    INDEX
    Explanations

    Code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     питания
    -0.07
     права
    -0.07
     Qty
    -0.07
    ження
    -0.06
     keer
    -0.06
    ering
    -0.06
     Numbers
    -0.06
     Academy
    -0.06
    (task
    -0.06
     Mej
    -0.06
    POSITIVE LOGITS
    Independent
    0.06
    coop
    0.06
    Northern
    0.06
    Design
    0.06
    Kent
    0.06
    atos
    0.06
    Characteristic
    0.06
    อฟ
    0.06
    Postal
    0.06
    소
    0.06
    Act Density 0.000%

    No Known Activations