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

    Neuronpedia

    INDEX
    Explanations

    USDA grades

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     conspired
    0.46
     계획
    0.45
    pK
    0.44
    прос
    0.44
     জোট
    0.44
    UEST
    0.44
    ഓം
    0.43
    𝚈
    0.43
    लेषण
    0.42
    gameOver
    0.42
    POSITIVE LOGITS
     Plus
    0.52
    ↵
    0.47
     Estas
    0.45
     Have
    0.43
     Jim
    0.43
     Exc
    0.43
    開幕
    0.43
     have
    0.42
     Darren
    0.42
     Andal
    0.42
    Act Density 0.004%

    No Known Activations