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

    Neuronpedia

    INDEX
    Explanations

    heat

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     prolifer
    -0.08
     borne
    -0.08
    纷
    -0.08
     Lending
    -0.07
    _gold
    -0.07
     liberties
    -0.07
     charm
    -0.07
     liberté
    -0.07
     freedom
    -0.07
     décision
    -0.07
    POSITIVE LOGITS
     సిద్ధ
    0.10
     מראש
    0.09
     javafx
    0.08
     Destination
    0.08
     തയ്യാറ
    0.08
     준비
    0.08
    _destination
    0.08
    ediator
    0.08
    ifadhi
    0.08
     హె
    0.08
    Act Density 0.003%

    No Known Activations