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

    Neuronpedia

    INDEX
    Explanations

    Common English articles/verbs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     knives
    -0.08
     emoji
    -0.07
    _exc
    -0.07
     MVP
    -0.07
    CHAIN
    -0.06
    ()
    -0.06
    _dir
    -0.06
    lfw
    -0.06
    Pix
    -0.06
    Equals
    -0.06
    POSITIVE LOGITS
    ................
    0.07
     painfully
    0.06
    isinden
    0.06
     illumination
    0.06
    utilus
    0.06
     stra
    0.06
    SpaceItem
    0.06
     р
    0.06
     Mandarin
    0.06
     queryString
    0.06
    Act Density 0.033%

    No Known Activations