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

    Neuronpedia

    INDEX
    Explanations

    )

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     erad
    -0.06
    ition
    -0.06
    IMER
    -0.06
     orgy
    -0.06
    assert
    -0.06
     RECEIVE
    -0.06
    die
    -0.06
     mediante
    -0.06
     serge
    -0.06
    收入
    -0.06
    POSITIVE LOGITS
    Favorite
    0.07
     Sau
    0.06
     haunted
    0.06
    购买
    0.06
    ाइव
    0.06
     molded
    0.06
     Projection
    0.06
    (JSON
    0.06
     Machine
    0.06
    .getList
    0.06
    Act Density 0.001%

    No Known Activations