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

    Neuronpedia

    INDEX
    Explanations

    required

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Flower
    -0.07
    Employees
    -0.07
     heav
    -0.06
    thumbnail
    -0.06
    _compat
    -0.06
    _BINDING
    -0.06
    ,param
    -0.06
    .social
    -0.06
     подк
    -0.06
    patches
    -0.06
    POSITIVE LOGITS
     连
    0.07
    验
    0.06
    US
    0.06
     armed
    0.06
     得
    0.06
    懂
    0.06
    وبی
    0.06
     emin
    0.06
     Jim
    0.06
     Tutor
    0.06
    Act Density 0.042%

    No Known Activations