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

    Neuronpedia

    INDEX
    Explanations

    phrases before questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     வாக்க
    0.40
    按
    0.40
    也是
    0.37
    otherap
    0.37
    SHA
    0.37
    adav
    0.37
    Mud
    0.37
    的功能
    0.37
    用户信息
    0.36
    म्स
    0.36
    POSITIVE LOGITS
     episode
    0.45
     achieved
    0.44
     ито
    0.44
     chape
    0.43
     ballad
    0.42
     bulb
    0.42
    ާ
    0.41
     suces
    0.40
     Yearbook
    0.40
     tono
    0.40
    Act Density 0.000%

    No Known Activations