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

    Neuronpedia

    INDEX
    Explanations

    numbered list items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     structs
    0.61
    gano
    0.57
    garakan
    0.55
     متنوع
    0.55
    끼
    0.54
     stents
    0.54
     Sunak
    0.51
    🤱
    0.51
     reqParams
    0.50
    𒐪
    0.50
    POSITIVE LOGITS
    User
    0.59
    пример
    0.53
    م
    0.52
    Error
    0.51
    ંક
    0.51
    P
    0.51
    Name
    0.50
    зо
    0.50
    H
    0.50
    و
    0.50
    Act Density 2.670%

    No Known Activations