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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     frm
    -0.08
     meetup
    -0.08
    统一
    -0.08
     expect
    -0.08
     csr
    -0.07
     textbox
    -0.07
     ARG
    -0.07
    现金
    -0.07
     backyard
    -0.07
     dataframe
    -0.07
    POSITIVE LOGITS
     further
    0.09
     계속
    0.09
     தொடர்ந்து
    0.08
    Further
    0.08
     Further
    0.08
    Until
    0.08
     weiterhin
    0.08
    さらに
    0.08
     மேலும்
    0.08
     തുടര
    0.08
    Act Density 0.057%

    No Known Activations