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

    Neuronpedia

    INDEX
    Explanations

    Returns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    classnames
    -0.07
    Encode
    -0.07
    emia
    -0.07
    olvable
    -0.07
     Haj
    -0.06
    (ph
    -0.06
    ètre
    -0.06
    EZ
    -0.06
     Crimea
    -0.06
    _Helper
    -0.06
    POSITIVE LOGITS
    devices
    0.08
     viv
    0.07
     playoffs
    0.07
    -setting
    0.07
     note
    0.07
     إ
    0.07
     pra
    0.06
     сост
    0.06
    ترنت
    0.06
     paperback
    0.06
    Act Density 0.001%

    No Known Activations