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

    Neuronpedia

    INDEX
    Explanations

    names followed by last names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ณี
    0.48
    批評
    0.46
    嬂
    0.44
    𝗝
    0.43
    ลา
    0.43
    StarGo
    0.43
     شرطونو
    0.42
    Closeup
    0.42
     вечером
    0.42
     утром
    0.42
    POSITIVE LOGITS
     committed
    0.50
     transfer
    0.44
     re
    0.43
     soph
    0.40
    transfer
    0.38
    ’
    0.38
     student
    0.38
     ot
    0.38
     commit
    0.38
     junior
    0.37
    Act Density 0.000%

    No Known Activations