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

    Neuronpedia

    INDEX
    Explanations

    lower

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ↵
    -0.07
    Returns
    -0.07
    saving
    -0.07
    اعد
    -0.06
    aving
    -0.06
     Кост
    -0.06
    ).
↵
    -0.06
     Coastal
    -0.06
    순
    -0.06
    ]>↵
    -0.06
    POSITIVE LOGITS
    endo
    0.06
     mül
    0.06
     Mercer
    0.06
    는지
    0.06
    onent
    0.06
    -shot
    0.06
     forgive
    0.06
    (requestCode
    0.06
     worship
    0.06
     imminent
    0.06
    Act Density 0.331%

    No Known Activations