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

    Neuronpedia

    INDEX
    Explanations

    tell me more about your needs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ETH
    0.52
    Hughes
    0.49
    Diabetes
    0.48
    گیر
    0.44
    Available
    0.43
     الأطفال
    0.43
    Minneapolis
    0.43
    Brick
    0.43
    FirstOrDefault
    0.43
     kişinin
    0.43
    POSITIVE LOGITS
    cheon
    0.51
     cruising
    0.46
    reibung
    0.46
    ography
    0.44
     shocking
    0.43
    jande
    0.43
     sizing
    0.43
     Villa
    0.43
    ̣ng
    0.43
    villa
    0.42
    Act Density 0.001%

    No Known Activations