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

    Neuronpedia

    INDEX
    Explanations

    protection

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     읽
    -0.06
    .IsNullOrEmpty
    -0.06
     bitter
    -0.06
     través
    -0.06
     bbw
    -0.06
    .espresso
    -0.06
    -online
    -0.06
     filmmakers
    -0.06
     жовт
    -0.06
    datatable
    -0.06
    POSITIVE LOGITS
    (errorMessage
    0.07
     spherical
    0.07
     Ap
    0.06
     Roots
    0.06
    ricia
    0.06
     pile
    0.06
     Strom
    0.06
     Cruise
    0.06
    (Py
    0.06
     mitigation
    0.06
    Act Density 0.066%

    No Known Activations