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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sioux
    -0.08
     players
    -0.07
     DUP
    -0.07
     NUMBER
    -0.07
     Treatment
    -0.07
     black
    -0.07
     Records
    -0.06
     Fak
    -0.06
     intervals
    -0.06
     very
    -0.06
    POSITIVE LOGITS
     geopolitical
    0.07
     catapult
    0.07
    popover
    0.07
                        
↵
    0.07
    .='
    0.06
    _miss
    0.06
    xito
    0.06
     человека
    0.06
     pricey
    0.06
    hipster
    0.06
    Act Density 0.023%

    No Known Activations