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

    Neuronpedia

    INDEX
    Explanations

    name

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    fi
    -0.07
     clear
    -0.07
    也正是
    -0.07
    ��
    -0.07
    pecia
    -0.07
    证
    -0.06
    ен
    -0.06
     patient
    -0.06
    Ay
    -0.06
    зн
    -0.06
    POSITIVE LOGITS
     worldwide
    0.07
    אט
    0.07
    abox
    0.07
    떼
    0.06
    舸
    0.06
     letras
    0.06
     בינלאומי
    0.06
    0.06
    📶
    0.06
     affidavit
    0.06
    Act Density 0.002%

    No Known Activations