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

    Neuronpedia

    INDEX
    Explanations

    White

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     DEF
    -0.07
     üy
    -0.07
     nuts
    -0.07
     rein
    -0.06
    _,↵
    -0.06
    >-->↵
    -0.06
     fonts
    -0.06
     břez
    -0.06
     cx
    -0.06
    德
    -0.06
    POSITIVE LOGITS
     broadcasts
    0.07
    (transaction
    0.06
    .ne
    0.06
    _COLORS
    0.06
    beros
    0.06
     Enforcement
    0.06
    (Properties
    0.06
    .tile
    0.06
     stabbing
    0.06
    ，被
    0.06
    Act Density 0.012%

    No Known Activations