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

    Neuronpedia

    INDEX
    Explanations

    )

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     далі
    -0.07
     noteworthy
    -0.06
    092
    -0.06
     agility
    -0.06
    .Contract
    -0.06
     IRC
    -0.06
    Violation
    -0.06
    -sync
    -0.06
     SEA
    -0.06
     MK
    -0.06
    POSITIVE LOGITS
     продаж
    0.07
    .person
    0.07
    -p
    0.06
    chluss
    0.06
     Pulitzer
    0.06
     rex
    0.06
     limestone
    0.06
    €
    0.06
     bustling
    0.06
     worlds
    0.06
    Act Density 1.366%

    No Known Activations