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

    Neuronpedia

    INDEX
    Explanations

    prepare support telescope use start

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    se
    0.42
    Cor
    0.42
    Det
    0.42
     or
    0.41
    amaz
    0.41
    ses
    0.40
    orov
    0.40
     expectant
    0.40
     avoids
    0.40
    EMA
    0.39
    POSITIVE LOGITS
    ใช่
    0.49
     mało
    0.47
     Technique
    0.46
     Promo
    0.46
     Eurostile
    0.46
     Hotel
    0.45
     유명
    0.45
     Sails
    0.44
    ifadə
    0.44
     Gitar
    0.44
    Act Density 0.004%

    No Known Activations