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

    Neuronpedia

    INDEX
    Explanations

    US state & federal initiatives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Uno
    0.65
    Wir
    0.60
    Strategic
    0.60
    Parts
    0.59
     Pic
    0.59
     Poli
    0.58
    Length
    0.57
     এমনি
    0.57
    Theory
    0.56
    Ad
    0.56
    POSITIVE LOGITS
     Humane
    0.82
    掑
    0.77
    texte
    0.77
    ások
    0.77
     issuing
    0.76
    ুমার
    0.75
    <unused984>
    0.73
    oise
    0.73
     Kisan
    0.72
     HAN
    0.72
    Act Density 0.001%

    No Known Activations