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

    Neuronpedia

    INDEX
    Explanations

    mark correct answers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .,"
    0.75
     bringing
    0.71
    ,“
    0.71
     thirties
    0.71
    .",
    0.67
    ,.
    0.67
    iary
    0.66
    ibh
    0.65
    ,\"
    0.65
    ,"
    0.64
    POSITIVE LOGITS
     □
    1.82
     √
    1.65
    □
    1.62
     ☐
    1.61
     ✓
    1.57
     ×
    1.51
     ★
    1.50
     ☑
    1.49
     ✔
    1.46
     △
    1.45
    Act Density 0.246%

    No Known Activations