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

    Neuronpedia

    INDEX
    Explanations

    chemical reactions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     stencil
    -0.07
     nur
    -0.06
     speaks
    -0.06
     Anna
    -0.06
    ]'↵
    -0.06
    nech
    -0.06
     zost
    -0.06
    pects
    -0.06
    ाओ
    -0.06
    �i
    -0.06
    POSITIVE LOGITS
    atted
    0.07
     síd
    0.07
    ──
    0.07
     باشگاه
    0.06
    cons
    0.06
     serde
    0.06
    CONS
    0.06
     PyErr
    0.06
     समर
    0.06
    创建
    0.06
    Act Density 0.058%

    No Known Activations