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

    Neuronpedia

    INDEX
    Explanations

    late nights rolling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Avila
    0.38
    django
    0.37
    轮
    0.37
    GC
    0.36
    PUR
    0.36
    tered
    0.35
    _{+}-
    0.35
     Norden
    0.35
    halogen
    0.35
    ルス
    0.35
    POSITIVE LOGITS
     researches
    0.49
     miro
    0.41
     miner
    0.40
     اخر
    0.40
     res
    0.39
    ⁶
    0.38
     fingert
    0.38
    ાઇન
    0.38
     deje
    0.37
     verbess
    0.37
    Act Density 0.001%

    No Known Activations