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

    Neuronpedia

    INDEX
    Explanations

    input field properties and event handlers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ের
    0.41
    screw
    0.39
     lacking
    0.37
    \%,
    0.37
    give
    0.36
     अलावा
    0.36
    स्तान
    0.35
    ে
    0.35
    setlength
    0.35
    𝙜
    0.34
    POSITIVE LOGITS
    ك
    0.42
    elser
    0.41
    im
    0.38
    us
    0.38
     doppio
    0.38
     sus
    0.37
    Liens
    0.37
    Như
    0.37
    UINT
    0.37
    тво
    0.37
    Act Density 0.033%

    No Known Activations