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

    Neuronpedia

    INDEX
    Explanations

    would followed by verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     zwią
    0.91
    กระท
    0.90
     والش
    0.85
    an
    0.82
    و
    0.82
    isIn
    0.82
    م
    0.81
    !\!\
    0.78
    л
    0.78
     volna
    0.78
    POSITIVE LOGITS
    den
    0.91
    ים
    0.89
    𝚢
    0.86
    ला
    0.82
    ்ப
    0.81
    Referee
    0.79
    mselves
    0.78
    st
    0.77
    sofar
    0.77
    合わせて
    0.76
    Act Density 0.213%

    No Known Activations