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

    Neuronpedia

    INDEX
    Explanations

    come, behind, mother, eat

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Cement
    0.46
     непосредственно
    0.46
     Sigma
    0.45
     конкре
    0.45
     SUPPORT
    0.45
     নিয়েও
    0.45
     অবজার
    0.44
     ניתן
    0.43
     מאוד
    0.43
    ésére
    0.43
    POSITIVE LOGITS
    etail
    0.55
     aturan
    0.54
    )
    0.52
    ේව
    0.48
    putted
    0.46
     හෝ
    0.46
     syllabus
    0.45
     speeding
    0.45
     skirts
    0.44
    speeds
    0.44
    Act Density 0.001%

    No Known Activations