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

    Neuronpedia

    INDEX
    Explanations

    comment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Cabin
    -0.07
    ACTIVE
    -0.06
    кат
    -0.06
     Phát
    -0.06
    Pretty
    -0.06
     secure
    -0.06
     enhancing
    -0.06
     loving
    -0.06
     largely
    -0.06
    Become
    -0.06
    POSITIVE LOGITS
     울
    0.08
    imizeBox
    0.07
    LK
    0.07
     ><
    0.07
    υ
    0.06
    .rl
    0.06
     друго
    0.06
     sistem
    0.06
     Considering
    0.06
     finalize
    0.06
    Act Density 0.001%

    No Known Activations