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

    Neuronpedia

    INDEX
    Explanations

    Burp Suite

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    typename
    0.56
     obstante
    0.55
     Reserved
    0.53
     boundary
    0.53
     bounded
    0.51
     skip
    0.51
    แบบ
    0.51
     заболе
    0.51
     break
    0.50
    Tob
    0.50
    POSITIVE LOGITS
     Buk
    0.79
    baden
    0.77
    AcOH
    0.75
     uitgenodigd
    0.72
     ape
    0.71
    蜞
    0.71
    ஷ்ய
    0.70
    icius
    0.70
    灞
    0.70
    ruptcy
    0.69
    Act Density 0.866%

    No Known Activations