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

    Neuronpedia

    INDEX
    Explanations

    pronunciation guides

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     също
    1.04
    Imidazole
    0.95
    Jadi
    0.92
    lact
    0.91
    EndX
    0.90
    Execute
    0.90
    École
    0.89
    Standing
    0.88
     animación
    0.87
    Съ
    0.87
    POSITIVE LOGITS
     multicol
    0.99
     metaphysical
    0.95
     generative
    0.95
     argumentative
    0.94
     sophisticated
    0.94
     strings
    0.93
     alphanumeric
    0.93
     anonym
    0.92
     logged
    0.92
     eclectic
    0.92
    Act Density 0.018%

    No Known Activations