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

    Neuronpedia

    INDEX
    Explanations

    breaking news or informative titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Description
    0.43
     Grundlage
    0.42
     bibliographic
    0.40
     information
    0.40
     azimuth
    0.39
     Correspondence
    0.39
     informations
    0.38
     Descriptions
    0.38
     いる
    0.38
     description
    0.38
    POSITIVE LOGITS
     How
    0.61
     Why
    0.59
    How
    0.59
     खुशखबरी
    0.57
    जानिए
    0.56
     BREAK
    0.56
    BREAK
    0.56
    Why
    0.54
    Breaking
    0.52
     WATCH
    0.51
    Act Density 0.014%

    No Known Activations