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

    Neuronpedia

    INDEX
    Explanations

    adding

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Watching
    -0.08
    Qualifications
    -0.08
     Ache
    -0.08
     Qualifications
    -0.08
    Qual
    -0.07
     qualifications
    -0.07
    Outside
    -0.07
    priet
    -0.07
     Qual
    -0.07
    Alarm
    -0.07
    POSITIVE LOGITS
     წერ
    0.09
    短信
    0.09
     tape
    0.08
     يدخل
    0.08
     millum
    0.08
    申博
    0.08
     געשריבן
    0.08
    সূচ
    0.08
     ceremony
    0.08
     գում
    0.08
    Act Density 0.034%

    No Known Activations