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

    Neuronpedia

    INDEX
    Explanations

    even

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    XB
    -0.07
    guna
    -0.07
    ンブ
    -0.07
    _endpoint
    -0.07
    енным
    -0.06
    위원
    -0.06
     membranes
    -0.06
    ار
    -0.06
    گیر
    -0.06
    рати
    -0.06
    POSITIVE LOGITS
     Gra
    0.07
    ]]=
    0.07
    Gr
    0.06
    Рµ
    0.06
    .change
    0.06
    Tel
    0.06
    .Gr
    0.06
    )$
    0.06
    .While
    0.06
    “One
    0.06
    Act Density 0.023%

    No Known Activations