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

    Neuronpedia

    INDEX
    Explanations

    want

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kıs
    -0.07
    简单
    -0.07
    around
    -0.06
     sky
    -0.06
     faction
    -0.06
     dry
    -0.06
     canoe
    -0.06
    隐藏
    -0.06
     numb
    -0.06
    루
    -0.06
    POSITIVE LOGITS
     fret
    0.06
     councill
    0.06
     vandalism
    0.06
    σκευ
    0.06
    (lhs
    0.06
    alloc
    0.06
    quate
    0.06
    UCCEEDED
    0.06
    $ret
    0.06
     retros
    0.06
    Act Density 0.012%

    No Known Activations