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

    Neuronpedia

    INDEX
    Explanations

    heaps and priority queues

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
    楒
    -0.07
    泜
    -0.07
    啴
    -0.07
    棓
    -0.07
    влад
    -0.07
    מטופ
    -0.07
     lineWidth
    -0.06
    🎲
    -0.06
    rokes
    -0.06
    POSITIVE LOGITS
    回
    0.08
    ％
    0.07
    ⽇
    0.07
    ��
    0.07
    Squared
    0.07
    권
    0.07
     toxicity
    0.07
    -util
    0.07
    ADDING
    0.06
     dB
    0.06
    Act Density 0.014%

    No Known Activations