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

    Neuronpedia

    INDEX
    Explanations

    make, cost, air

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Gosudarstvennyj
    0.55
    ́p
    0.54
     فونبټ
    0.53
     കമ്മി
    0.52
    ༦
    0.52
     الاستاذ
    0.50
    會有
    0.49
     كوم
    0.48
    gimento
    0.48
    ்துறை
    0.46
    POSITIVE LOGITS
     for
    0.67
    ier
    0.67
    ies
    0.66
    ness
    0.60
     in
    0.59
    man
    0.59
    ing
    0.57
    ler
    0.57
    iness
    0.55
    away
    0.54
    Act Density 1.645%

    No Known Activations