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

    Neuronpedia

    INDEX
    Explanations

    fact-checking

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <unused924>
    0.73
    <unused2016>
    0.73
    <unused632>
    0.72
    <unused601>
    0.69
    <unused404>
    0.69
    <unused1823>
    0.68
    <unused1917>
    0.68
     hashedPassword
    0.67
    unnel
    0.66
     sdx
    0.66
    POSITIVE LOGITS
    <h3>
    1.02
    <h4>
    0.88
    Posted
    0.87
    <h1>
    0.83
    posted
    0.78
    <h2>
    0.76
    <h5>
    0.74
    例文帳に追加
    0.73
    <h6>
    0.72
     Posted
    0.70
    Act Density 0.000%

    No Known Activations