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

    Neuronpedia

    INDEX
    Explanations

    ="

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    cla
    -0.07
                                    
    -0.06
                                                ↵
    -0.06
    Visited
    -0.06
    .El
    -0.06
                                                    ↵
    -0.06
    .callback
    -0.06
     reinforce
    -0.06
     boutique
    -0.06
     اخ
    -0.06
    POSITIVE LOGITS
     jezd
    0.06
     dies
    0.06
     seaborn
    0.06
    elleicht
    0.06
     उसस
    0.06
     sandals
    0.06
     marrying
    0.06
    Andrew
    0.06
     싱글
    0.06
    _news
    0.06
    Act Density 0.002%

    No Known Activations