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

    Neuronpedia

    INDEX
    Explanations

    API access and antigen tests

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    大数据
    0.49
    TextViewStyle
    0.48
     كلمات
    0.46
     kleiner
    0.44
     வாழ்க்கை
    0.44
     எழு
    0.44
    芎
    0.43
     المقد
    0.42
    चेता
    0.42
     Frühstück
    0.42
    POSITIVE LOGITS
     и
    0.58
    D
    0.55
    R
    0.53
    and
    0.52
    J
    0.52
     and
    0.50
    ID
    0.49
    W
    0.48
    dep
    0.47
    P
    0.47
    Act Density 0.001%

    No Known Activations