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

    Neuronpedia

    INDEX
    Explanations

    Fake text and streams

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     धर
    -0.07
    _gift
    -0.06
     reflex
    -0.06
    ams
    -0.06
    {}'.
    -0.06
    904
    -0.06
    .teacher
    -0.06
     член
    -0.06
    estre
    -0.06
    uns
    -0.06
    POSITIVE LOGITS
     intellectually
    0.07
     AVL
    0.06
    /The
    0.06
    );
↵
↵
    0.06
    Removed
    0.06
     DAYS
    0.06
    _VERSION
    0.06
    Snapshot
    0.06
    听到
    0.06
    票
    0.06
    Act Density 0.002%

    No Known Activations