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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pb
    -0.07
    til
    -0.06
     Camera
    -0.06
    Piece
    -0.06
    itational
    -0.06
     star
    -0.06
    察
    -0.06
    ührung
    -0.06
     determinant
    -0.06
    Bro
    -0.06
    POSITIVE LOGITS
    .horizontal
    0.07
    　r
    0.07
     Nội
    0.06
     đốc
    0.06
        
↵    
↵
    0.06
     캐
    0.06
    .links
    0.06
    ие
    0.06
    δη
    0.06
    Tip
    0.06
    Act Density 0.068%

    No Known Activations