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

    Neuronpedia

    INDEX
    Explanations

    does not constitute

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     yeah
    0.38
    ime
    0.37
    ovia
    0.36
     dépassant
    0.36
     luis
    0.35
     ██
    0.35
     લ
    0.35
     listBox
    0.35
    ','"+
    0.35
    ım
    0.34
    POSITIVE LOGITS
     Typed
    0.37
    ANGAN
    0.36
    滪
    0.36
    安全的
    0.34
    त्त
    0.34
    ոլ
    0.34
     reconocido
    0.33
     открытия
    0.33
    positivo
    0.33
     요청
    0.33
    Act Density 0.016%

    No Known Activations