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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     із
    -0.08
     hàng
    -0.08
     slu
    -0.08
    �
    -0.08
    铺
    -0.08
    .orm
    -0.07
    <form
    -0.07
     धन्यवाद
    -0.07
    ार्थ
    -0.07
     سازی
    -0.07
    POSITIVE LOGITS
     భావ
    0.09
     తీవ్ర
    0.09
    ละเอียด
    0.08
     Dig
    0.08
    Dump
    0.08
    _RUNNING
    0.08
    Covid
    0.07
     Dump
    0.07
     concussion
    0.07
     DIG
    0.07
    Act Density 0.017%

    No Known Activations