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

    Neuronpedia

    INDEX
    Explanations

    purpose or function

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Laravel
    0.34
     User
    0.33
     Regex
    0.32
    utente
    0.32
     Postgres
    0.30
     Fiverr
    0.30
     Baş
    0.29
    ers
    0.29
     Nvidia
    0.29
    os
    0.29
    POSITIVE LOGITS
     trest
    0.26
    IRCONIUM
    0.25
     schist
    0.24
     hydrolysis
    0.24
    Chlor
    0.24
    Hors
    0.24
     meadow
    0.24
    COVERY
    0.24
    넬
    0.24
    THA
    0.24
    Act Density 0.009%

    No Known Activations