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

    Neuronpedia

    INDEX
    Explanations

    measurements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ��
    -0.07
    هل
    -0.06
    .Native
    -0.06
    	buf
    -0.06
    "How
    -0.06
    .Logger
    -0.06
    qua
    -0.06
    "Well
    -0.06
    겨
    -0.06
    answers
    -0.06
    POSITIVE LOGITS
     strengths
    0.07
    NDAR
    0.06
     establishing
    0.06
     experiencing
    0.06
    мом
    0.06
    子の
    0.06
     topics
    0.06
     пит
    0.06
    ーマ
    0.05
     esk
    0.05
    Act Density 0.166%

    No Known Activations