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

    Neuronpedia

    INDEX
    Explanations

    important considerations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    *
    0.96
     *
    0.80
     quite
    0.76
     necessary
    0.73
     જવાબ
    0.72
    *'
    0.72
     essentially
    0.71
     Necessary
    0.71
    *(
    0.71
    *$
    0.70
    POSITIVE LOGITS
    染色
    0.90
    istir
    0.88
    oston
    0.85
     صد
    0.84
    年生
    0.84
    ningar
    0.83
    洱
    0.83
    条件下
    0.80
     वेतन
    0.79
    ellae
    0.77
    Act Density 0.031%

    No Known Activations