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

    Neuronpedia

    INDEX
    Explanations

    Starting or initiating

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     struggled
    -0.07
     constructed
    -0.07
    <Block
    -0.07
     holds
    -0.07
     true
    -0.07
     distorted
    -0.07
     configured
    -0.06
    Yes
    -0.06
    _FAST
    -0.06
     creeping
    -0.06
    POSITIVE LOGITS
    ะแ
    0.07
     سین
    0.07
    ��
    0.07
    字段
    0.06
    роб
    0.06
     Move
    0.06
    egree
    0.06
     emphasis
    0.06
    anche
    0.06
     tanı
    0.06
    Act Density 0.161%

    No Known Activations