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

    Neuronpedia

    INDEX
    Explanations

    tax

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _DRIVER
    -0.08
     plo
    -0.07
     відріз
    -0.07
    范围
    -0.07
     swift
    -0.06
    rend
    -0.06
     cute
    -0.06
     Swansea
    -0.06
     брат
    -0.06
     script
    -0.06
    POSITIVE LOGITS
     tax
    0.09
     taxes
    0.09
     Tax
    0.09
     Thank
    0.08
     Taxes
    0.08
    Tax
    0.07
     TAX
    0.07
    -tax
    0.07
    Thank
    0.07
    tok
    0.07
    Act Density 0.016%

    No Known Activations