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

    Neuronpedia

    INDEX
    Explanations

    physics concepts

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    estens
    0.79
     phyt
    0.76
     quilts
    0.75
     Ga
    0.74
    नाच्या
    0.71
    ilin
    0.71
     JO
    0.69
    மிகு
    0.68
     Erskine
    0.67
     arable
    0.67
    POSITIVE LOGITS
     đợi
    0.74
     номе
    0.67
     வீரர்கள்
    0.65
     দফা
    0.63
    জনকে
    0.58
    Signature
    0.58
     дз
    0.58
     fmt
    0.57
    zmdi
    0.57
    Patient
    0.57
    Act Density 0.006%

    No Known Activations