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

    Neuronpedia

    INDEX
    Explanations

    say that

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     oxidación
    0.40
    omeric
    0.39
    electronic
    0.38
    ainen
    0.37
    loem
    0.37
     agon
    0.37
     vicious
    0.37
    jiang
    0.37
     কথাই
    0.37
     alla
    0.36
    POSITIVE LOGITS
    第七
    0.41
     පෙ
    0.39
    iflower
    0.38
     stoked
    0.38
    //
    0.38
    iszt
    0.37
     NOMBRE
    0.35
    ద్య
    0.35
     journaliste
    0.35
    第五
    0.35
    Act Density 0.001%

    No Known Activations