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

    Neuronpedia

    INDEX
    Explanations

    titles and labels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    cours
    0.37
    yatiti
    0.36
    Therm
    0.36
    ្ឋ
    0.36
     ലി
    0.36
    তীশ
    0.36
     GRI
    0.36
     vů
    0.35
    でしょう
    0.35
    itating
    0.35
    POSITIVE LOGITS
    spd
    0.45
     Folks
    0.43
     folks
    0.41
     campuses
    0.38
    {
    0.38
     अधिका
    0.38
     perspekt
    0.38
     spectrum
    0.37
     suppress
    0.37
            
    0.36
    Act Density 0.000%

    No Known Activations