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

    Neuronpedia

    INDEX
    Explanations

    with or together

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     beraten
    0.38
    ంచరీలు
    0.36
    rimps
    0.33
    andel
    0.33
    Dif
    0.33
    adhat
    0.33
     ස්ථා
    0.32
    Cmd
    0.32
     qnt
    0.32
     consid
    0.32
    POSITIVE LOGITS
     contigo
    1.84
     вместе
    1.83
     conmigo
    1.74
     함께
    1.72
     μαζί
    1.71
     معه
    1.70
     comigo
    1.69
     junto
    1.66
     bersama
    1.65
     alongside
    1.63
    Act Density 0.036%

    No Known Activations