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

    Neuronpedia

    INDEX
    Explanations

    -style

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    HIGH
    -0.07
    …………………………………………
    -0.06
     mph
    -0.06
     worm
    -0.06
     Cape
    -0.06
    Avg
    -0.06
    _intersection
    -0.06
     thanks
    -0.06
    gresql
    -0.05
     Kas
    -0.05
    POSITIVE LOGITS
    ]=$
    0.08
     Styles
    0.08
    esor
    0.07
    ับร
    0.07
    LTE
    0.07
    ностью
    0.07
    gere
    0.07
    шая
    0.07
     exhausted
    0.06
    anna
    0.06
    Act Density 0.001%

    No Known Activations