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

    Neuronpedia

    INDEX
    Explanations

    Numbers ending in 0

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ArrayList
    -0.08
     aisle
    -0.07
     chants
    -0.06
     nt
    -0.06
     پی
    -0.06
    thrown
    -0.06
     Q
    -0.06
    зь
    -0.06
    办理
    -0.06
    //
    -0.06
    POSITIVE LOGITS
    .DE
    0.07
    CJK
    0.06
     Joint
    0.06
     yere
    0.06
     Comprehensive
    0.06
     köln
    0.06
     münchen
    0.06
     недостат
    0.06
    ]').
    0.06
    КО
    0.06
    Act Density 0.057%

    No Known Activations