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

    Neuronpedia

    INDEX
    Explanations

    technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    roys
    -0.07
     ()
    -0.06
    imity
    -0.06
    .argsort
    -0.06
     los
    -0.06
    -0.06
    VP
    -0.06
     desi
    -0.06
    _water
    -0.06
    (",")↵
    -0.06
    POSITIVE LOGITS
    βε
    0.07
    
    0.07
     Debt
    0.07
     Universidad
    0.07
    cerer
    0.06
     NF
    0.06
    år
    0.06
    Sound
    0.06
    TRACE
    0.06
     Awards
    0.06
    Act Density 0.163%

    No Known Activations