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

    Neuronpedia

    INDEX
    Explanations

    say "into"

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    To
    1.48
     To
    1.43
    to
    1.32
     to
    1.23
     TO
    0.98
    ToServer
    0.92
     toa
    0.91
    ToOne
    0.90
    ToAction
    0.89
    ToExp
    0.89
    POSITIVE LOGITS
     змін
    0.36
     прогре
    0.35
     кожен
    0.34
    ட்ச
    0.34
     教え
    0.34
     reproducibility
    0.34
    เปลี่ยนแปลง
    0.33
    unctive
    0.33
     воспроиз
    0.33
    地产
    0.32
    Act Density 0.018%

    No Known Activations