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

    Neuronpedia

    INDEX
    Explanations

    geographic names and places

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ni
    0.73
    N
    0.65
    v
    0.62
    ,
    0.61
    ter
    0.61
     complicado
    0.59
    es
    0.59
    ij
    0.59
    ian
    0.58
    <h2>
    0.57
    POSITIVE LOGITS
     for
    0.87
    ת
    0.84
     be
    0.81
     are
    0.81
     as
    0.74
    </h4>
    0.68
     can
    0.67
    </h3>
    0.64
    </sub>
    0.64
    。"
    0.63
    Act Density 0.019%

    No Known Activations