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

    Neuronpedia

    INDEX
    Explanations

    Code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Dow
    -0.07
    [U
    -0.07
    KeyDown
    -0.07
     Cooperation
    -0.07
     detectors
    -0.06
     lng
    -0.06
     Dental
    -0.06
    -L
    -0.06
    =G
    -0.06
     ediyorum
    -0.06
    POSITIVE LOGITS
    .Cache
    0.07
     mostrar
    0.07
     درمان
    0.06
    　　　 　
    0.06
     fron
    0.06
     зер
    0.06
    ΟΥΣ
    0.06
    \Auth
    0.06
    �
    0.06
    瑟
    0.06
    Act Density 0.002%

    No Known Activations