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

    Neuronpedia

    INDEX
    Explanations

    massive overkill

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     しかし
    0.60
     However
    0.59
     [
    0.57
     ஆனால்
    0.55
     Speaking
    0.55
     Namun
    0.52
     Interestingly
    0.51
     HOWEVER
    0.51
     Thus
    0.50
     however
    0.48
    POSITIVE LOGITS
    <h2>
    1.10
    <table>
    1.02
    <h3>
    0.64
    <h4>
    0.55
    Duration
    0.55
    Normdaten
    0.55
    |}
    0.51
    </td>
    0.49
     tableau
    0.47
    Ét
    0.46
    Act Density 0.001%

    No Known Activations