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

    Neuronpedia

    INDEX
    Explanations

    Vicuna model

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Meg
    0.45
    meg
    0.44
    Meg
    0.43
     megap
    0.40
     Hee
    0.40
    绎
    0.39
     अधीक्षक
    0.39
     Ansari
    0.39
     সংস্কৃতি
    0.38
     meg
    0.38
    POSITIVE LOGITS
     vic
    0.79
    Vic
    0.78
     Vic
    0.76
    vic
    0.70
     VIC
    0.65
    una
    0.59
    uña
    0.54
    UNA
    0.52
    VIC
    0.50
    Vict
    0.50
    Act Density 0.005%

    No Known Activations