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

    Neuronpedia

    INDEX
    Explanations

    narrative ideas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ત
    0.50
     баскет
    0.50
     предприятий
    0.48
    Memory
    0.47
    onomics
    0.47
     આપ
    0.46
     xét
    0.46
    entemente
    0.46
     ไหร่
    0.46
     Asimismo
    0.46
    POSITIVE LOGITS
     sinusitis
    0.50
    '
    0.49
    د
    0.48
     contagious
    0.47
    ާމ
    0.47
     agg
    0.46
     stance
    0.46
     delegated
    0.45
     dotnet
    0.45
     recieved
    0.45
    Act Density 0.000%

    No Known Activations