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

    Neuronpedia

    INDEX
    Explanations

    computer code and terminology

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    して
    -0.07
    Numeric
    -0.06
     přiz
    -0.06
     Shapiro
    -0.06
     Friends
    -0.06
    ès
    -0.06
    subcategory
    -0.06
     princ
    -0.06
    其实
    -0.06
    Goal
    -0.06
    POSITIVE LOGITS
     �
    0.08
    ILE
    0.07
     PH
    0.07
     Vote
    0.07
     znění
    0.07
     sta
    0.06
     sildenafil
    0.06
    따
    0.06
    YST
    0.06
    .OP
    0.06
    Act Density 0.069%

    No Known Activations