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

    Neuronpedia

    INDEX
    Explanations

    script

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    DP
    -0.06
     visiting
    -0.06
     ballots
    -0.06
     Badge
    -0.06
    -four
    -0.06
     Γκ
    -0.06
     trustee
    -0.06
     �
    -0.06
     Radius
    -0.06
     ten
    -0.06
    POSITIVE LOGITS
     الکترون
    0.07
     وضعیت
    0.07
    [,]
    0.07
    】【
    0.07
     nitel
    0.07
    lement
    0.07
     온라인
    0.07
    ."',
    0.07
    िरफ
    0.06
    Flight
    0.06
    Act Density 0.004%

    No Known Activations