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

    Neuronpedia

    INDEX
    Explanations

    code identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    逻
    -0.88
    готов
    -0.85
     AppCompat
    -0.82
    𖡼
    -0.81
    فش
    -0.80
     Wilt
    -0.79
     made
    -0.79
     exploración
    -0.77
     пище
    -0.77
    ticion
    -0.77
    POSITIVE LOGITS
    ille
    0.90
    貼り
    0.87
     regal
    0.85
    MPH
    0.81
     unearthed
    0.81
     coworkers
    0.80
    obe
    0.80
     onbe
    0.79
     Historically
    0.77
     neutr
    0.77
    Act Density 0.061%

    No Known Activations