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

    Neuronpedia

    INDEX
    Explanations

    The Trevor Project

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     momentum
    0.58
     around
    0.55
     generally
    0.54
     current
    0.54
     not
    0.54
     specific
    0.53
     alternative
    0.53
     past
    0.52
     specifically
    0.52
     temporary
    0.52
    POSITIVE LOGITS
    <unused196>
    0.74
    <unused369>
    0.73
    <unused1933>
    0.67
    <unused258>
    0.66
    <unused1893>
    0.65
    <unused2060>
    0.64
    rollees
    0.64
     ۋە
    0.64
     Balliye
    0.64
    <unused1710>
    0.64
    Act Density 0.194%

    No Known Activations