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

    Neuronpedia

    INDEX
    Explanations

    purification processes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ilia
    -0.07
    �
    -0.07
    _crypto
    -0.07
    bash
    -0.07
    ница
    -0.07
     texture
    -0.06
     Albert
    -0.06
    ницу
    -0.06
    /current
    -0.06
    Dao
    -0.06
    POSITIVE LOGITS
     TAX
    0.07
    希
    0.07
     serpent
    0.06
     mệ
    0.06
    。↵↵↵↵↵↵
    0.06
     hướng
    0.06
     �
    0.06
     Excell
    0.06
     Müslüman
    0.06
    ?"↵↵↵↵
    0.06
    Act Density 0.029%

    No Known Activations