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

    Neuronpedia

    INDEX
    Explanations

    learning to code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Lockhart
    0.48
     Ef
    0.46
     immensely
    0.46
     Bower
    0.46
     Sleeve
    0.45
     Palace
    0.45
     Folding
    0.45
     Auburn
    0.44
     Constance
    0.44
     anda
    0.43
    POSITIVE LOGITS
    ross
    0.47
    autres
    0.45
     других
    0.45
    aghan
    0.45
    wiki
    0.44
    otros
    0.43
    ints
    0.43
     autres
    0.43
     коричне
    0.42
     outras
    0.42
    Act Density 0.000%

    No Known Activations