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

    Neuronpedia

    INDEX
    Explanations

    legal terms and laws

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     "*"
    0.38
     rye
    0.38
    ozems
    0.37
    ámenes
    0.36
     commas
    0.36
    我們先
    0.36
    Dame
    0.36
    okhlov
    0.35
     segni
    0.35
    rept
    0.35
    POSITIVE LOGITS
     Confederacy
    0.41
     কর্তৃক
    0.40
     Lightning
    0.39
    ił
    0.38
     Cub
    0.38
    wand
    0.38
     ది
    0.37
    tetrahydro
    0.37
     passed
    0.36
     lightning
    0.36
    Act Density 0.002%

    No Known Activations