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

    Neuronpedia

    INDEX
    Explanations

    code comparisons/logic

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Receive
    -0.07
    ライ
    -0.07
    celand
    -0.07
    ך
    -0.07
     items
    -0.07
    ᵁ
    -0.07
    ℮
    -0.07
    .Async
    -0.07
    �
    -0.06
    .tele
    -0.06
    POSITIVE LOGITS
     essentially
    0.07
    '})
    0.07
    )}>
    0.07
    .RadioButton
    0.07
    &&
    0.07
     исполни
    0.07
     purported
    0.06
     basically
    0.06
    ”，
    0.06
    ']>
    0.06
    Act Density 0.044%

    No Known Activations