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

    Neuronpedia

    INDEX
    Explanations

    scenario appending

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Late
    0.40
     कायदा
    0.40
     rays
    0.39
     theses
    0.39
     verpflicht
    0.38
     KV
    0.38
     ஒப்ப
    0.38
     позд
    0.38
     meus
    0.37
     pensamientos
    0.37
    POSITIVE LOGITS
    NER
    0.43
    Mostly
    0.42
    $("
    0.40
    ﻲ
    0.38
    mage
    0.38
    ators
    0.38
    often
    0.38
    OfType
    0.37
    tried
    0.37
    serrat
    0.37
    Act Density 0.000%

    No Known Activations