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

    Neuronpedia

    INDEX
    Explanations

    what if

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     imen
    0.39
     Utilis
    0.38
     adiab
    0.38
     Scheduler
    0.38
     Verte
    0.37
    umna
    0.37
     Wiring
    0.37
     Acoustic
    0.37
     ➤
    0.36
     Blitz
    0.36
    POSITIVE LOGITS
     mash
    0.45
     abundance
    0.41
     excursions
    0.41
    aping
    0.40
     experiments
    0.39
    ંધ
    0.38
    orph
    0.38
    ‏‏
    0.38
    Corruption
    0.38
    Abandoned
    0.37
    Act Density 0.000%

    No Known Activations