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

    Neuronpedia

    INDEX
    Explanations

    Abbreviations and codes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     doPost
    -0.07
     Ming
    -0.07
     spree
    -0.07
    .getNumber
    -0.07
     thủ
    -0.06
    mov
    -0.06
     hospodář
    -0.06
    .Invalid
    -0.06
    ..'
    -0.06
     pyplot
    -0.06
    POSITIVE LOGITS
     pacing
    0.07
     breadcrumb
    0.06
     SSH
    0.06
    ognito
    0.06
     освіт
    0.06
    ีนาคม
    0.06
    Uuid
    0.06
    \Storage
    0.06
    ρκεια
    0.06
    柜
    0.06
    Act Density 0.039%

    No Known Activations