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

    Neuronpedia

    INDEX
    Explanations

    sequencing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    楷
    -0.08
    黄昏
    -0.07
    颇为
    -0.07
    珠宝
    -0.07
    INPUT
    -0.07
     faithful
    -0.07
    _ADC
    -0.07
     conjunction
    -0.07
     endorsement
    -0.07
    -push
    -0.07
    POSITIVE LOGITS
     Pract
    0.07
    מדינ
    0.07
    谝
    0.06
    𝙺
    0.06
    ulator
    0.06
     jed
    0.06
     Selenium
    0.06
     polic
    0.06
    很多
    0.06
    न
    0.06
    Act Density 0.005%

    No Known Activations