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

    Neuronpedia

    INDEX
    Explanations

    ne

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Laboratories
    -0.07
    reatest
    -0.07
     objects
    -0.06
     pets
    -0.06
    /events
    -0.06
    variation
    -0.06
     Pos
    -0.06
     Springs
    -0.06
     Beach
    -0.06
    いる
    -0.06
    POSITIVE LOGITS
    _comp
    0.07
     нему
    0.07
    �
    0.07
     جمع
    0.07
     mijn
    0.07
    _EXP
    0.06
    端
    0.06
     담
    0.06
    巡
    0.06
    坦
    0.06
    Act Density 0.000%

    No Known Activations