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

    Neuronpedia

    INDEX
    Explanations

    but however

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     companion
    0.49
     perspective
    0.49
     school
    0.47
     square
    0.47
     reactive
    0.47
     settings
    0.46
     definite
    0.46
    льное
    0.46
     chance
    0.46
     beautiful
    0.45
    POSITIVE LOGITS
    ಸಿ
    0.48
    ání
    0.47
    Surprisingly
    0.46
    म्मद
    0.46
     конку
    0.46
    lycerin
    0.46
     Surprisingly
    0.45
    Competing
    0.45
     Negoti
    0.45
    isiaj
    0.44
    Act Density 0.010%

    No Known Activations