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

    Neuronpedia

    INDEX
    Explanations

    finds inspiration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     règlement
    0.43
     でき
    0.43
     พิจิก
    0.41
    下記
    0.41
    ेटा
    0.39
    Neces
    0.39
    ่ะ
    0.38
    ૧
    0.38
    稈
    0.38
    笕
    0.38
    POSITIVE LOGITS
     mildly
    0.45
     influencers
    0.44
     hybrids
    0.44
     rarely
    0.42
     Δ
    0.41
     "
    0.40
     faster
    0.39
    ([]
    0.39
     neither
    0.39
    неш
    0.38
    Act Density 0.000%

    No Known Activations