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

    Neuronpedia

    INDEX
    Explanations

    android

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ढ
    -0.07
    -Sep
    -0.07
     )↵↵↵↵↵↵↵↵
    -0.06
    })",
    -0.06
     mailbox
    -0.06
    <Post
    -0.06
    Legacy
    -0.06
     етап
    -0.06
    :";
↵
    -0.06
    avra
    -0.06
    POSITIVE LOGITS
    PAIR
    0.07
    .so
    0.06
     magg
    0.06
    mpr
    0.06
     ZEND
    0.06
     tb
    0.06
    .sulake
    0.06
    -hidden
    0.06
    -n
    0.06
     اسلام
    0.06
    Act Density 0.025%

    No Known Activations