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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     chickens
    -0.08
     afinal
    -0.08
     chica
    -0.08
     guinea
    -0.08
     craftsmen
    -0.07
    surname
    -0.07
     эксперимент
    -0.07
    Chief
    -0.07
     ikk
    -0.07
     hunt
    -0.07
    POSITIVE LOGITS
     prohibited
    0.12
     unacceptable
    0.09
     DOCUMENT
    0.09
     contraind
    0.09
     taboo
    0.09
     verboten
    0.09
    违法吗
    0.09
     verboden
    0.08
     prohibition
    0.08
    禁止
    0.08
    Act Density 0.039%

    No Known Activations