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

    Neuronpedia

    INDEX
    Explanations

    STEM related terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    }"
    0.31
     Homework
    0.30
     Appointment
    0.29
     Ux
    0.29
     निबंध
    0.29
     Michel
    0.29
     scaffolds
    0.29
     memos
    0.29
    生日
    0.29
    acrylate
    0.29
    POSITIVE LOGITS
    鑄
    0.35
    AudioAsset
    0.34
    ősz
    0.33
     SEP
    0.32
    ImageBox
    0.32
     karakteristik
    0.32
     Azz
    0.31
    靂
    0.31
    arda
    0.31
    IAM
    0.31
    Act Density 0.000%

    No Known Activations