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

    Neuronpedia

    INDEX
    Explanations

    simple, reflecting, proportionally

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     decision
    0.40
    Moz
    0.40
    ℕ
    0.39
    ივ
    0.38
    adó
    0.37
     evolutionary
    0.37
    醋
    0.37
    Mozilla
    0.36
     decisions
    0.36
     亀
    0.36
    POSITIVE LOGITS
    ग्रस्त
    0.42
     Wab
    0.39
     කරයි
    0.38
     disheart
    0.38
     tightened
    0.38
     erle
    0.37
     किफ
    0.37
    کی
    0.36
     бер
    0.36
     мате
    0.35
    Act Density 0.000%

    No Known Activations