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

    Neuronpedia

    INDEX
    Explanations

    Making things up

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    文献
    -0.07
     Cary
    -0.07
    _domain
    -0.07
     한국
    -0.06
    .load
    -0.06
     nn
    -0.06
     antagonist
    -0.06
     ctl
    -0.06
     Cs
    -0.06
     membership
    -0.06
    POSITIVE LOGITS
     çıkar
    0.07
    expiry
    0.06
    hesive
    0.06
    ogh
    0.06
     nouvelle
    0.06
    sizlik
    0.06
     spaces
    0.06
    ами
    0.06
    cit
    0.06
     tooltips
    0.06
    Act Density 0.004%

    No Known Activations