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

    Neuronpedia

    INDEX
    Explanations

    text processing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     revis
    -0.07
    orz
    -0.07
    trying
    -0.07
    Uni
    -0.06
     cmds
    -0.06
     labor
    -0.06
     tap
    -0.06
     banc
    -0.06
    edicine
    -0.06
     دنبال
    -0.06
    POSITIVE LOGITS
    733
    0.07
    _PORTS
    0.07
     Fallout
    0.06
    waukee
    0.06
    (QtCore
    0.06
    (credentials
    0.06
    决
    0.06
     Oxygen
    0.06
    792
    0.06
    ????????
    0.06
    Act Density 0.001%

    No Known Activations