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

    Neuronpedia

    INDEX
    Explanations

    вывод

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     blender
    -0.06
     Kom
    -0.06
    cts
    -0.06
    _take
    -0.06
    .nc
    -0.06
    .employee
    -0.06
    acket
    -0.06
     archivo
    -0.06
     erfahren
    -0.06
    iked
    -0.06
    POSITIVE LOGITS
    ③
    0.08
     renderItem
    0.07
    .dto
    0.07
    　　 　
    0.07
    系列
    0.07
    dto
    0.07
     HIM
    0.07
     VIN
    0.06
    INO
    0.06
     اتحاد
    0.06
    Act Density 0.005%

    No Known Activations