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

    Neuronpedia

    INDEX
    Explanations

    depicting a

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     οποίος
    0.42
     पहुंचते
    0.41
    deleted
    0.40
     обуча
    0.38
     सकेंगे
    0.38
    instruct
    0.38
    insights
    0.37
    customize
    0.37
    automate
    0.37
    鳗
    0.37
    POSITIVE LOGITS
     oriental
    0.39
     ring
    0.38
     tree
    0.38
     cyclic
    0.37
    ucci
    0.37
     ceramic
    0.37
     hierarchical
    0.37
     ք
    0.37
     OSX
    0.36
     Einzel
    0.35
    Act Density 0.000%

    No Known Activations