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

    Neuronpedia

    INDEX
    Explanations

    NAICS code and NOTES

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    type
    0.40
    mute
    0.38
    கை
    0.38
    merk
    0.36
    fone
    0.35
    栢
    0.35
     chilly
    0.34
    semester
    0.34
     detector
    0.34
     घ
    0.34
    POSITIVE LOGITS
     anticipating
    0.37
     WE
    0.36
     Созда
    0.35
    壌
    0.35
     създа
    0.35
     storm
    0.34
     idiosyncratic
    0.33
     oblast
    0.33
     primi
    0.33
    믹
    0.33
    Act Density 0.001%

    No Known Activations