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

    Neuronpedia

    INDEX
    Explanations

    vectors and linear algebra

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     handbook
    -0.08
    רע
    -0.08
     crowned
    -0.08
    -ede
    -0.08
    faf
    -0.08
     incent
    -0.07
     obsessed
    -0.07
     режима
    -0.07
    .herokuapp
    -0.07
     record
    -0.07
    POSITIVE LOGITS
     placeholder
    0.08
     Orb
    0.08
    _placeholder
    0.08
    �
    0.08
     Diagram
    0.08
     că
    0.08
    0.08
     Append
    0.07
     각각
    0.07
     Mes
    0.07
    Act Density 0.030%
    No Known Activations