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

    Neuronpedia

    INDEX
    Explanations

    automata and language theory

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Scale
    -0.08
     journal
    -0.07
    693
    -0.07
    -scale
    -0.07
    Click
    -0.07
     Scale
    -0.07
    方向
    -0.07
    561
    -0.06
    bottom
    -0.06
    riel
    -0.06
    POSITIVE LOGITS
     �
    0.06
     Genç
    0.06
    FileNotFoundException
    0.06
     Кост
    0.06
     zájem
    0.06
     herr
    0.06
    bomb
    0.05
     Kota
    0.05
    _MetaData
    0.05
    ModelError
    0.05
    Act Density 0.022%

    No Known Activations