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

    Neuronpedia

    INDEX
    Explanations

    double spaced

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     coalesce
    0.98
    ighting
    0.97
    Temporal
    0.97
     vigour
    0.95
    檛
    0.95
    ampions
    0.94
     способность
    0.94
     muons
    0.93
     কাঠামো
    0.92
     microcos
    0.91
    POSITIVE LOGITS
     doss
    1.07
    árd
    1.00
    記載
    0.91
     быть
    0.89
    तांत्रिक
    0.88
    cia
    0.87
    jacoco
    0.85
     travel
    0.85
    மாண
    0.84
     NAACP
    0.84
    Act Density 0.000%

    No Known Activations