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

    Neuronpedia

    INDEX
    Explanations

    speaking or quotes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Although
    0.40
     Additionally
    0.39
     svm
    0.38
    Additionally
    0.37
     Although
    0.37
     through
    0.36
     spie
    0.36
     হলেও
    0.35
    ссмотрим
    0.35
     zusätzlich
    0.35
    POSITIVE LOGITS
    Honestly
    0.51
    if
    0.51
    people
    0.49
     Honestly
    0.49
    YOU
    0.48
    Tôi
    0.47
    you
    0.46
    yes
    0.46
     আমি
    0.46
    আমি
    0.46
    Act Density 0.001%

    No Known Activations