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
    ungeon
    -0.06
    lerimiz
    -0.06
    OMP
    -0.06
    ระด
    -0.06
    ного
    -0.06
    Santa
    -0.06
    Swipe
    -0.06
    entario
    -0.06
    Saved
    -0.06
    Serial
    -0.06
    POSITIVE LOGITS
     offences
    0.07
     bev
    0.07
    'u
    0.07
    'ex
    0.07
     guten
    0.07
     ऋ
    0.06
    (sizeof
    0.06
     пит
    0.06
     OleDb
    0.06
    шими
    0.06
    Act Density 0.001%

    No Known Activations