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

    Neuronpedia

    INDEX
    Explanations

    also, addition, furthermore

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     another
    0.84
    Surprisingly
    0.84
     Another
    0.83
    Another
    0.81
    岧
    0.73
    Throughout
    0.72
     Surprisingly
    0.72
    another
    0.70
     exclusively
    0.70
     очередной
    0.69
    POSITIVE LOGITS
     גם
    1.34
     myös
    1.34
     juga
    1.30
     همچنین
    1.30
     also
    1.30
     cũng
    1.29
     inoltre
    1.29
     também
    1.25
     также
    1.23
     essentially
    1.23
    Act Density 0.608%

    No Known Activations