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

    Neuronpedia

    INDEX
    Explanations

    step-by-step guides

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     electron
    -0.08
     recol
    -0.07
     statue
    -0.07
     initials
    -0.07
    猜
    -0.07
     arcs
    -0.07
     proportion
    -0.07
    íns
    -0.07
     uphill
    -0.07
     mentioned
    -0.07
    POSITIVE LOGITS
     hoogwaardige
    0.09
     도움이
    0.09
     comenzar
    0.09
     begyn
    0.08
     Hieronder
    0.08
     uitgebreide
    0.08
     börja
    0.08
     commencer
    0.08
     начинают
    0.08
     начинает
    0.08
    Act Density 0.028%

    No Known Activations