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

    Neuronpedia

    INDEX
    Explanations

    product description

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     surely
    -0.07
     хто
    -0.07
     dramatically
    -0.06
    ='".$
    -0.06
     unsub
    -0.06
    ationally
    -0.06
    PointerException
    -0.06
     rather
    -0.06
    Further
    -0.06
    Merc
    -0.06
    POSITIVE LOGITS
    0.17
     \
    0.08
    i
    0.08
     hadn
    0.08
     
    0.07
    n
    0.07
    -
    0.07
    .vertx
    0.07
     wouldn
    0.07
    in
    0.07
    Act Density 1.147%

    No Known Activations