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

    Neuronpedia

    INDEX
    Explanations

    amendments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     jus
    -0.07
     azi
    -0.07
     Ric
    -0.07
    unities
    -0.06
     CSRF
    -0.06
    Difference
    -0.06
     Kostenlos
    -0.06
     ricerca
    -0.06
    -di
    -0.06
     costo
    -0.06
    POSITIVE LOGITS
     Senate
    0.09
     Amend
    0.08
    Penn
    0.07
     amendment
    0.07
     amendments
    0.07
     amended
    0.07
     amend
    0.06
     EntryPoint
    0.06
     compromise
    0.06
     khoản
    0.06
    Act Density 0.005%

    No Known Activations