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

    Neuronpedia

    INDEX
    Explanations

    ive

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     کردند
    -0.07
     �
    -0.07
    ा�
    -0.06
    bank
    -0.06
     */,
    -0.06
     DOCUMENT
    -0.06
    )=
    -0.06
     pollution
    -0.06
    ือข
    -0.06
    !).
    -0.06
    POSITIVE LOGITS
    (confirm
    0.07
    ritt
    0.06
     UIL
    0.06
    athi
    0.06
     maç
    0.06
    riger
    0.06
    /items
    0.06
     Toni
    0.06
     Rag
    0.06
     sci
    0.06
    Act Density 0.001%

    No Known Activations