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

    Neuronpedia

    INDEX
    Explanations

    wise, reliable, thoughtful

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    sei
    0.35
    Β
    0.35
     Bett
    0.34
    <sup>
    0.33
     beetroot
    0.32
     Darth
    0.31
    zant
    0.31
     согласно
    0.31
     creamy
    0.31
     octahedral
    0.31
    POSITIVE LOGITS
    उनके
    0.40
     নজর
    0.36
     njegov
    0.35
    ोल
    0.33
    اویز
    0.33
    rparam
    0.33
    রাজের
    0.33
    瞍
    0.32
     Onun
    0.32
     Fisher
    0.31
    Act Density 0.016%

    No Known Activations