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

    Neuronpedia

    INDEX
    Explanations

    theoretical

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     passwords
    -0.06
     Johann
    -0.06
     ebay
    -0.06
    moire
    -0.06
     dra
    -0.06
     solicit
    -0.06
    beiter
    -0.06
    .cfg
    -0.06
     Peterson
    -0.06
     brewed
    -0.06
    POSITIVE LOGITS
     theoretical
    0.08
     }*/↵
    0.07
     ương
    0.07
    .control
    0.07
     theoretically
    0.07
    ssf
    0.06
    ")]
↵
    0.06
     programmer
    0.06
     дем
    0.06
     minus
    0.06
    Act Density 0.007%

    No Known Activations