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

    Neuronpedia

    INDEX
    Explanations

    buckle up

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     चीज
    0.33
     collectives
    0.33
     EEOC
    0.32
    ের
    0.31
     SSSR
    0.31
    াসী
    0.31
     adat
    0.31
     चीज़
    0.31
    s
    0.29
     oxidative
    0.29
    POSITIVE LOGITS
     heavily
    0.38
     назад
    0.36
     softly
    0.34
     още
    0.34
     silently
    0.33
    Ч
    0.33
     throats
    0.33
    軽く
    0.32
     quietly
    0.32
     furiously
    0.31
    Act Density 0.034%

    No Known Activations