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

    Neuronpedia

    INDEX
    Explanations

    structural markers and common pairings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sym
    0.42
     murmur
    0.41
     response
    0.41
     syndrome
    0.41
     sympathies
    0.40
     tro
    0.39
     biofuels
    0.39
     difficulties
    0.38
     premier
    0.37
     acoustics
    0.37
    POSITIVE LOGITS
    䳕
    0.41
    bracketing
    0.39
     Änderungen
    0.38
     добро
    0.36
     カジュアル
    0.36
     ドラ
    0.36
     ›
    0.36
     •
    0.36
     outlining
    0.36
     丶
    0.36
    Act Density 0.007%

    No Known Activations