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

    Neuronpedia

    INDEX
    Explanations

    Specifications and technical details

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    gers
    -0.07
    Aut
    -0.07
    参与
    -0.06
    台灣
    -0.06
    ino
    -0.06
    INO
    -0.06
    _IDENT
    -0.06
    .Region
    -0.06
    fet
    -0.06
     *)↵↵
    -0.06
    POSITIVE LOGITS
     MessageType
    0.08
    (upload
    0.07
    علق
    0.07
    ُل
    0.07
    caught
    0.06
    (scale
    0.06
     اختلاف
    0.06
     DEST
    0.06
    ّ
    0.06
     Successful
    0.06
    Act Density 0.177%

    No Known Activations