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

    Neuronpedia

    INDEX
    Explanations

    Python

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ghi
    -0.07
    elements
    -0.06
    桥
    -0.06
     Robbie
    -0.06
    �
    -0.06
    .ba
    -0.06
     غ
    -0.06
     thử
    -0.06
    底
    -0.06
     dư
    -0.06
    POSITIVE LOGITS
     chords
    0.06
     Blazers
    0.06
    PERT
    0.06
    _MESSAGE
    0.06
    ',)↵
    0.06
     raspberry
    0.06
    ,)↵
    0.06
     kullanıcı
    0.06
    ICLES
    0.06
    CustomLabel
    0.06
    Act Density 0.010%

    No Known Activations