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

    Neuronpedia

    INDEX
    Explanations

    code structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    یل
    1.06
    ன
    1.01
    =("
    1.00
    añas
    0.95
    DBOutput
    0.93
    тись
    0.93
    置いて
    0.90
    限于
    0.89
     GCBO
    0.88
    AIS
    0.85
    POSITIVE LOGITS
     doctrine
    0.97
    ️
    0.87
    essed
    0.83
     quorum
    0.82
     Mons
    0.81
    wann
    0.81
     Deficiency
    0.80
     wah
    0.78
     wanna
    0.78
     bearing
    0.77
    Act Density 0.002%

    No Known Activations