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

    Neuronpedia

    INDEX
    Explanations

    threats and distress

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     which
    0.82
    begin
    0.80
    llll
    0.77
     sharpen
    0.73
     who
    0.72
     찾는
    0.72
     प्रॉब्लम
    0.71
     intention
    0.71
     finder
    0.71
     straightening
    0.71
    POSITIVE LOGITS
     rapporto
    0.74
    ія
    0.73
    纽约
    0.70
     duas
    0.70
     varietà
    0.69
    🦓
    0.68
    profiss
    0.68
    র্জাতিক
    0.68
    ,‎
    0.68
     caso
    0.67
    Act Density 0.001%

    No Known Activations