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

    Neuronpedia

    INDEX
    Explanations

    not

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bicycle
    -0.07
     campaign
    -0.07
    جيب
    -0.07
    Setting
    -0.07
    إق
    -0.07
     Inspired
    -0.07
     Stand
    -0.07
     pricing
    -0.07
     easiest
    -0.06
    cast
    -0.06
    POSITIVE LOGITS
     improves
    0.07
    📎
    0.07
     "\",
    0.07
     (.
    0.07
     (),↵
    0.07
    _EXCEPTION
    0.07
    สะ
    0.07
    (norm
    0.06
    副作用
    0.06
    (..
    0.06
    Act Density 0.027%

    No Known Activations