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

    Neuronpedia

    INDEX
    Explanations

    a huge

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     eventuali
    0.83
     немного
    0.79
     Änderungen
    0.78
     약간
    0.78
     ligeramente
    0.76
     Slightly
    0.76
     βοη
    0.75
     Änderung
    0.74
    Occasionally
    0.74
     légèrement
    0.74
    POSITIVE LOGITS
     chronic
    1.74
     crippling
    1.56
     systemic
    1.55
     severe
    1.45
     chronically
    1.45
     glaring
    1.43
     pervasive
    1.40
     Chronic
    1.38
     worsening
    1.37
    Chronic
    1.37
    Act Density 0.495%

    No Known Activations