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

    Neuronpedia

    INDEX
    Explanations

    IP address

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     تضيفلها
    -0.55
    ddots
    -0.50
    MENAFN
    -0.48
     Walkover
    -0.47
    ANEOUS
    -0.46
    ]^{-
    -0.46
    τως
    -0.46
     CreateTagHelper
    -0.45
    исленность
    -0.45
     digress
    -0.44
    POSITIVE LOGITS
    <bos>
    0.93
    '
    0.67
    Name
    0.65
    set
    0.63
     of
    0.60
    ↵↵
    0.59
    name
    0.59
    ↵
    0.56
    berdayakan
    0.54
    _
    0.54
    Act Density 0.770%

    No Known Activations