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

    Neuronpedia

    INDEX
    Explanations

    prior states

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ucle
    -0.08
    _NO
    -0.07
    isti
    -0.07
    ව
    -0.07
    .execute
    -0.07
    uthor
    -0.07
    _num
    -0.07
    핥
    -0.07
    �
    -0.06
     контр
    -0.06
    POSITIVE LOGITS
    开盘
    0.07
    几个月
    0.06
    的作用
    0.06
    的有效
    0.06
     careers
    0.06
    Two
    0.06
    blocked
    0.06
    MENTS
    0.06
    แบร
    0.06
    rieben
    0.06
    Act Density 0.033%

    No Known Activations