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

    Neuronpedia

    INDEX
    Explanations

    entities followed by delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ವಾರು
    0.92
    hkse
    0.88
    <unused2082>
    0.87
    Messaging
    0.82
    latego
    0.82
    各种
    0.81
    Các
    0.81
    Ли
    0.81
    无论
    0.81
    หมือน
    0.80
    POSITIVE LOGITS
     /
    1.04
     (“
    0.97
     with
    0.96
     (
    0.92
    /
    0.89
     +
    0.89
     “
    0.87
     ‘
    0.84
     ("
    0.82
     @
    0.81
    Act Density 0.233%

    No Known Activations