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

    Neuronpedia

    INDEX
    Explanations

    Bar

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    j
    0.97
     ,
    0.90
    ている
    0.85
    ने
    0.82
    <h2>
    0.79
    u
    0.79
    ן
    0.79
    .,
    0.78
    ní
    0.78
    .
    0.76
    POSITIVE LOGITS
    ak
    0.72
     Bar
    0.72
     bar
    0.68
     بار
    0.64
    ре
    0.64
     бар
    0.63
    0.61
     স্বরে
    0.60
    alkyl
    0.59
    এত
    0.59
    Act Density 0.000%

    No Known Activations