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

    Neuronpedia

    INDEX
    Explanations

    generations Gen3, Gen5

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sector
    0.53
     camp
    0.52
     ultrast
    0.50
     franchise
    0.50
     destac
    0.50
     spectrum
    0.49
     main
    0.49
     operational
    0.49
     Training
    0.49
     highlights
    0.49
    POSITIVE LOGITS
    фе
    0.51
     douleur
    0.49
    Angelo
    0.48
    I
    0.48
    Ella
    0.48
    눅
    0.48
    Eggs
    0.47
     آئینہ
    0.47
    udence
    0.47
    ONTO
    0.46
    Act Density 0.000%

    No Known Activations