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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     JAVA
    -0.07
    (Position
    -0.06
     congestion
    -0.06
     thanh
    -0.06
    _iter
    -0.06
    TargetException
    -0.06
    elligent
    -0.06
    _Game
    -0.06
     پیشنهاد
    -0.06
     Brothers
    -0.06
    POSITIVE LOGITS
     digestive
    0.07
    ेट
    0.07
     ol
    0.07
     Cycle
    0.06
    ầm
    0.06
     bağ
    0.06
    ichern
    0.06
     currently
    0.06
     abbreviation
    0.06
     absolute
    0.06
    Act Density 0.001%

    No Known Activations