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

    Neuronpedia

    INDEX
    Explanations

    Time in the past

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     exemption
    -0.08
     AttributeSet
    -0.07
     Arguments
    -0.07
     redeemed
    -0.06
     Geile
    -0.06
    𬙋
    -0.06
    ;",↵
    -0.06
     Atom
    -0.06
    独立董事
    -0.06
     Bentley
    -0.06
    POSITIVE LOGITS
     FetchType
    0.07
    わかって
    0.07
     tháng
    0.07
    _found
    0.07
    この
    0.07
     הרבה
    0.07
    身材
    0.07
    Hugh
    0.07
    .echo
    0.07
    G
    0.07
    Act Density 0.038%

    No Known Activations