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

    Neuronpedia

    INDEX
    Explanations

    find by id

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     UID
    0.42
     individual
    0.40
     Unique
    0.37
     ಗುರು
    0.37
     URLs
    0.37
     unique
    0.37
     getString
    0.37
    getUrl
    0.36
    msgSender
    0.36
     UserId
    0.36
    POSITIVE LOGITS
    OrFail
    0.41
    מור
    0.40
     throwIfNotFound
    0.40
    由
    0.38
    꼴
    0.38
    PROVIDED
    0.37
     gifted
    0.37
     poking
    0.37
    冶
    0.37
    Asked
    0.36
    Act Density 0.002%

    No Known Activations