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

    Neuronpedia

    INDEX
    Explanations

    computations and values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Demonstrate
    0.39
     Solid
    0.38
     Deposits
    0.37
    ，
    0.37
    solid
    0.37
     denn
    0.36
     sólido
    0.36
    ,\
    0.36
     Deposit
    0.36
    лове
    0.36
    POSITIVE LOGITS
     pendants
    0.43
     terbaik
    0.42
     elettron
    0.42
    نگ
    0.42
    contenedor
    0.42
    ži
    0.42
    clusters
    0.41
     meilleure
    0.41
     pendant
    0.40
    anjutan
    0.40
    Act Density 0.000%

    No Known Activations