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

    Neuronpedia

    INDEX
    Explanations

    null

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     drunk
    -0.07
    aying
    -0.06
     웨
    -0.06
    PAL
    -0.06
    ΕΡ
    -0.06
     века
    -0.06
     excludes
    -0.06
     KL
    -0.06
    ена
    -0.06
    بة
    -0.06
    POSITIVE LOGITS
    .lines
    0.07
     ushort
    0.06
     silly
    0.06
    <TResult
    0.06
    함
    0.06
     decrement
    0.06
    #Region
    0.06
     exterior
    0.06
    졌다
    0.06
    иг
    0.06
    Act Density 0.007%

    No Known Activations