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

    Neuronpedia

    INDEX
    Explanations

    musical pieces

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     scritt
    0.46
    其實
    0.41
     scrive
    0.41
    cot
    0.40
     écriv
    0.39
    れば
    0.39
     образ
    0.38
    袮
    0.38
    वान
    0.37
     schrij
    0.37
    POSITIVE LOGITS
    Prompt
    0.48
    Tabs
    0.43
     prompts
    0.43
     Prompt
    0.42
    Piece
    0.42
     generative
    0.42
    SBI
    0.42
    VIS
    0.42
    Buttons
    0.42
    Quality
    0.42
    Act Density 0.003%

    No Known Activations