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

    Neuronpedia

    INDEX
    Explanations

    conversations and dialogue

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     luxe
    -0.08
     parfait
    -0.08
    闶
    -0.07
     Państwo
    -0.07
    农业科技
    -0.07
    .spring
    -0.07
    ﱇ
    -0.07
    mıştır
    -0.07
     девушк
    -0.07
     SMP
    -0.07
    POSITIVE LOGITS
    COORD
    0.07
    চ
    0.07
     �
    0.07
     waves
    0.07
     dej
    0.07
    (ref
    0.07
    ليل
    0.07
    日期
    0.07
    סק
    0.07
    韶
    0.07
    Act Density 0.014%

    No Known Activations