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

    Neuronpedia

    INDEX
    Explanations

    Department

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    踶
    -0.07
    _THRESH
    -0.07
    ures
    -0.07
    udes
    -0.07
    ��
    -0.06
    ví
    -0.06
     premises
    -0.06
    ้าง
    -0.06
    étique
    -0.06
    Dia
    -0.06
    POSITIVE LOGITS
    睡眠
    0.07
     attainment
    0.07
    面粉
    0.07
     epith
    0.07
    writer
    0.07
     Editorial
    0.07
     textColor
    0.07
    轨
    0.06
    歌曲
    0.06
    0.06
    Act Density 0.009%

    No Known Activations