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

    Neuronpedia

    INDEX
    Explanations

    important considerations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    zkod
    0.48
     følgende
    0.47
     legalized
    0.46
     untapped
    0.46
     улучшения
    0.46
    慢慢
    0.44
     खुशखबरी
    0.44
     அன்பு
    0.43
    مكن
    0.43
     исследований
    0.43
    POSITIVE LOGITS
     throw
    0.46
    INESS
    0.46
    Formatting
    0.43
    $?
    0.43
     torso
    0.43
    Cleaning
    0.42
    OCH
    0.41
    ya
    0.40
    BOOL
    0.40
     sion
    0.40
    Act Density 0.067%

    No Known Activations