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

    Neuronpedia

    INDEX
    Explanations

    listing categories and options

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ხმარ
    0.46
    வரும்
    0.42
     ambigu
    0.38
     hurriedly
    0.37
    ቸውን
    0.37
     그럼
    0.37
    ađ
    0.36
    лимпий
    0.35
     британ
    0.35
     حاول
    0.34
    POSITIVE LOGITS
     etc
    0.49
    etc
    0.45
     वगैरह
    0.44
     тощо
    0.43
     أو
    0.43
     &/
    0.43
     type
    0.41
     maupun
    0.41
     등으로
    0.40
     or
    0.40
    Act Density 0.190%

    No Known Activations