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

    Neuronpedia

    INDEX
    Explanations

    resilience

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     सौ
    -0.08
    另
    -0.08
     Proud
    -0.08
     उचित
    -0.08
     Santos
    -0.08
    erah
    -0.07
     Registrar
    -0.07
     मृत
    -0.07
    ေတာ္
    -0.07
     строго
    -0.07
    POSITIVE LOGITS
     resilience
    0.11
    Against
    0.10
     against
    0.10
     구축
    0.10
     resil
    0.09
     Against
    0.09
     gegenüber
    0.09
     resilient
    0.09
    against
    0.08
    ilience
    0.08
    Act Density 0.013%

    No Known Activations