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

    Neuronpedia

    INDEX
    Explanations

    winning contests

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     foaf
    0.86
     pemrograman
    0.81
     finne
    0.81
    Accelerometer
    0.77
     trouver
    0.76
    Ethoxy
    0.76
    していきます
    0.76
    лийн
    0.75
    ለመ
    0.75
    每周
    0.75
    POSITIVE LOGITS
     against
    1.67
     Against
    1.35
    against
    1.31
     during
    1.25
     versus
    1.22
     featuring
    1.21
     en
    1.19
    Against
    1.19
     AGAINST
    1.17
     marred
    1.16
    Act Density 0.012%

    No Known Activations