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

    Neuronpedia

    INDEX
    Explanations

    quantifiers and entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ian
    0.50
    8
    0.50
    li
    0.44
    ci
    0.44
    loaded
    0.44
    odan
    0.44
    Os
    0.44
    game
    0.43
    arde
    0.43
    ll
    0.43
    POSITIVE LOGITS
     какие
    0.51
     cuttings
    0.51
     ochrony
    0.50
     elettronica
    0.49
    ቈ
    0.49
     некоторые
    0.49
     quelles
    0.48
     quarant
    0.48
     Еўропы
    0.48
     algumas
    0.47
    Act Density 0.003%

    No Known Activations