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

    Neuronpedia

    INDEX
    Explanations

    easily, kolay, facile

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    proof
    0.55
     broni
    0.54
    ী
    0.54
    و
    0.53
    ৭
    0.52
    evil
    0.52
     unavoid
    0.52
     pouvoir
    0.51
    am
    0.51
     bullpen
    0.50
    POSITIVE LOGITS
     easily
    0.63
     suisse
    0.61
     hardly
    0.59
     fácilmente
    0.58
    很容易
    0.57
    ˡ
    0.57
     بسه
    0.55
    看出
    0.54
     अगदी
    0.54
    вна
    0.54
    Act Density 0.483%

    No Known Activations