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

    Neuronpedia

    INDEX
    Explanations

    the word "established" and words that sometimes go near it such as "peaceful"

    oai_token-act-pair · gemini-2.0-flash

    established

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    }();
    -0.88
    ."));
    -0.83
    )";
    -0.79
    ]');
    -0.75
    ()]);
    -0.73
    jsonwebtoken
    -0.73
    دانشنامهٔ
    -0.72
    ).]
    -0.72
    ]";
    -0.72
    ()");
    -0.72
    POSITIVE LOGITS
      
    0.68
     the
    0.63
     
    0.62
     
    0.56
    IntoConstraints
    0.56
     "
    0.56
     As
    0.56
    HOLD
    0.56
    tilizers
    0.52
    multirow
    0.52
    Act Density 0.577%

    No Known Activations