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

    Neuronpedia

    INDEX
    Explanations

    ChatALL

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ڈپ
    0.41
    ቴክ
    0.39
    英
    0.38
     रचनात्मक
    0.36
    surf
    0.36
    Vern
    0.36
    copter
    0.36
    Dol
    0.35
    క్టర్
    0.35
     soins
    0.35
    POSITIVE LOGITS
    ヨー
    0.41
     partisans
    0.41
     Artificial
    0.39
     Jaw
    0.39
     „
    0.38
     Alh
    0.38
     agreg
    0.38
     compromised
    0.38
     agglomer
    0.38
    javac
    0.38
    Act Density 0.004%

    No Known Activations