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

    Neuronpedia

    INDEX
    Explanations

    Remaining

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rounds
    -0.08
     MsgBox
    -0.07
     nowhere
    -0.07
     Advis
    -0.07
    Blob
    -0.07
    (rank
    -0.07
     proxy
    -0.07
     balloons
    -0.07
    ible
    -0.07
     pp
    -0.07
    POSITIVE LOGITS
    ogue
    0.07
    anganese
    0.07
    이크
    0.07
    degrees
    0.06
     postav
    0.06
    ichte
    0.06
     موبایل
    0.06
    开放
    0.06
    ?><?
    0.06
     MES
    0.06
    Act Density 0.025%

    No Known Activations