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

    Neuronpedia

    INDEX
    Explanations

    -(

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     История
    -0.07
     merc
    -0.07
    Cols
    -0.06
     cuckold
    -0.06
    neg
    -0.06
     Bundes
    -0.06
    งแต
    -0.06
    Phil
    -0.06
    _vc
    -0.06
    _EVT
    -0.06
    POSITIVE LOGITS
    胆
    0.07
    invitation
    0.06
     admission
    0.06
    .Α
    0.06
     lookup
    0.06
    (state
    0.06
     Kavanaugh
    0.06
     DMA
    0.06
     stayed
    0.06
    ator
    0.06
    Act Density 0.012%

    No Known Activations