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

    Neuronpedia

    INDEX
    Explanations

    competition

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ARGS
    -0.07
     promotes
    -0.07
    VIEW
    -0.07
    DDD
    -0.07
     LatLng
    -0.07
     interview
    -0.06
    ình
    -0.06
    _comm
    -0.06
    ंभ
    -0.06
     Supplements
    -0.06
    POSITIVE LOGITS
     surpassed
    0.08
     surpass
    0.07
    ))==
    0.07
     gunshot
    0.06
    imenti
    0.06
    :");
↵
    0.06
    ?")↵
    0.06
    ếp
    0.06
    <>();
↵
    0.06
    arena
    0.06
    Act Density 0.042%

    No Known Activations