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

    Neuronpedia

    INDEX
    Explanations

    formal language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     DATA
    -0.07
    _is
    -0.07
    --,
    -0.07
    _URI
    -0.07
    orted
    -0.07
    $status
    -0.06
     bers
    -0.06
     broth
    -0.06
    --
    -0.06
     buyers
    -0.06
    POSITIVE LOGITS
     therefore
    0.07
     poorest
    0.06
     virtually
    0.06
     timely
    0.06
     escol
    0.06
     legally
    0.06
     petty
    0.06
     заст
    0.06
    ордин
    0.06
     constantly
    0.06
    Act Density 0.036%

    No Known Activations